POPULARITY
Categories
313 episodes with MLP
284 episodes with MLP
67 episodes with MLP
42 episodes with MLP
53 episodes with MLP
61 episodes with MLP
53 episodes with MLP
25 episodes with MLP
33 episodes with MLP
57 episodes with MLP
48 episodes with MLP
61 episodes with MLP
17 episodes with MLP
57 episodes with MLP
30 episodes with MLP
34 episodes with MLP
13 episodes with MLP
12 episodes with MLP
4 episodes with MLP
17 episodes with MLP
22 episodes with MLP
7 episodes with MLP
7 episodes with MLP
4 episodes with MLP
8 episodes with MLP
3 episodes with MLP
3 episodes with MLP
6 episodes with MLP
4 episodes with MLP
6 episodes with MLP
63 episodes with MLP
8 episodes with MLP
2 episodes with MLP
6 episodes with MLP
3 episodes with MLP
2 episodes with MLP
Brooklyn is the team nobody wants to draw, New Jersey may have made the wrong pick, and St. Louis looks like a machine built to steamroll the bracket. If you care about the MLP playoff picture, this is the episode that makes the whole weekend feel bigger. Nico and Zane break down the biggest decisions heading into New York, including the shocking New Jersey vs. Brooklyn matchup choice, whether lineup changes are coming, and why the Shock, Fives, and Flash all have very different paths to the title. They also rank every possible finals matchup and explain which championship pairing would be electric, which would be a letdown, and why this postseason could finally deliver the rivalry pickleball has been waiting for. Then Grayson Goldin joins the show for one of the most powerful comeback stories in pro pickleball. Six months after suffering two strokes and losing his ability to speak, Grayson returns to the court and wins gold in Shenzhen, describing the fear, the recovery, the rehab, and the mental battle behind getting his game and his voice back.
Send us Fan MailAnother week of King of the Court and there's plenty to get into.Tyler and Jimmy preview the MLP semifinals and finals in Central Park, including Brooklyn vs. New Jersey, Dallas vs. St. Louis, DreamBreaker possibilities, and Jimmy making a VERY confident prediction about who will win the championship.Then we get into one of the biggest behind-the-scenes issues in professional pickleball: partnerships. Why are players constantly dropping partners? When is it justified? Does loyalty still matter? And should the PPA implement a 30-day rule preventing last-minute partner changes?We also discuss the APP defaulting a team over mismatched uniforms, the new Tesla x Selkirk paddle, some surprising World Pickleball Rankings, and Nick Kyrgios' recent suspension and Stack's decision to stand behind him.00:00 – Jimmy's Undershirt Debate00:49 – Welcome to King of the Court01:35 – The Football Team That Refused to Play03:13 – Football Brawl & Scott Steiner Connection04:01 – Pickler Universe05:32 – Dominator06:17 – Montis Pickleball07:52 – Jimmy's Pickleball Comeback & "Kill List"10:49 – MLP New York Preview12:13 – Jackie Kawamoto Gets Engaged13:58 – Brooklyn vs. New Jersey Predictions16:12 – Jimmy Predicts a Brooklyn Upset16:51 – Dallas vs. St. Louis Predictions18:16 – Who Wins the MLP Championship?19:12 – MLP Takes Over Central Park20:39 – APP Defaults a Team Over Their Uniforms23:54 – Tesla x Selkirk's New Paddle26:20 – Pro Pickleball's Partnership Problem28:02 – Is Loyalty Dead in Pro Pickleball?29:39 – When Is Dropping a Partner Justified?31:04 – Should There Be a 30-Day Rule?33:44 – PPA's New Qualification Rules34:31 – The World Pickleball Rankings Get Weird36:59 – Can Players Game the Ranking System?39:35 – Grayson Goldin Wins in Malaysia40:22 – Pickleball Nationals Preview41:04 – KOTC Live Podcast at Nationals41:47 – Club Pickleball Mastermind43:09 – Jimmy's Barefoot Lawn-Mowing Advice43:47 – Nick Kyrgios' Cocaine Suspension45:46 – Why Stack Stood Behind Kyrgios48:12 – The Hypocrisy Controversy49:31 – Final Thoughts on Kyrgios50:15 – Wrapping UpWebsite: https://www.tylerloong.com/ KOTC All Accesshttps://www.youtube.com/channel/UCDiH-sjthLCovD8i79-AkWg/joinCode “KOTC” for insane discounts at: https://www.clubpickleballmastermind.com/kotcCode "KOTC" at Montispickleball.com KOTC Merch - Use “KOTC” kitchpickleball.comNEW KOTC DISCORD https://discord.com/invite/kNR65mBemfNEW KOTC CAMEOhttps://www.cameo.com/morekotcInstagram: Tyler's IG - @tyler.loong Jimmy's IG - @jimmymiller_pbKOTC IG - @morekingofthecourt Facebook: / tyler.loong --Support the show
Turnbuckle Tavern is powered by G FUEL and Official Dick Lazer. Use code TAVERN for 20% off at GFUEL.com and DickLazers.com. Episode 206 of Wrestling Tonight begins with one of the biggest "what ifs" surrounding John Cena's retirement run. Adam Copeland says he believes Tony Khan would have allowed him to step outside AEW for one final Edge vs. Cena match in WWE. Copeland made it clear that nothing was ever formally proposed, Tony was never actually asked and WWE never officially rejected the idea, but his belief is that AEW would not have been the obstacle. It is especially interesting because Cena and Edge were so important to one another's careers, and a final match could have been more than nostalgia. It could have been one of those rare moments where WWE and AEW put the promotional rivalry aside for something that made sense historically. We look at whether it was ever realistic, what Tony allowing it would have meant for the relationship between the two companies and why one of the most obvious matches for Cena's farewell never got beyond the hypothetical stage. We then turn to AEW, where Kenny Omega and Will Ospreay have made their All In match increasingly personal. The story has become about far more than simply determining who the better wrestler is, with their history stretching back through PWG, New Japan and Ospreay's years of being compared to the standard Omega established before him. That rivalry now intersects with Ospreay's return from neck fusion surgery and his attempt to prove that he has finally surpassed Omega. Their sit-down with Renee Paquette revisited Omega questioning whether Ospreay ever truly replaced him and the lingering issue of Ospreay needing Don Callis' involvement to defeat Kenny at Forbidden Door. Omega then crossed another line by bringing Ospreay's family into the discussion before ultimately putting him through a table with the One-Winged Angel. With Ospreay back in front of his home crowd at Wembley after everything surrounding his surgery and recovery, AEW has turned this into one of the most important matches of his career. Pat McAfee's WWE future also appears increasingly clear. More than a year after stepping away from Raw commentary because of burnout, McAfee has added another major ESPN responsibility by joining Monday Night Countdown throughout the NFL season. His daily show will also broadcast from the site of Monday Night Football each week while he continues working College GameDay on Saturdays. McAfee has now reiterated that he does not intend to return to WWE television following the WrestleMania 42 stipulation where Cody Rhodes defeating Randy Orton meant McAfee would leave WWE programming for good. He even acknowledged that he may have been wrong about Cody after spending the storyline attacking him. Wrestling stipulations can always be undone, but between McAfee's comments and an ESPN schedule that now consumes both Saturdays and Mondays throughout football season, a regular WWE return looks increasingly unlikely. Josh Alexander is also moving closer to an in-ring return just over four months after undergoing knee surgery. Alexander resurfaced on Maple Leaf Pro Wrestling Mayhem and confronted Stu Grayson, teasing the eventual unification of MLP's Canadian Championship. Alexander has remained champion throughout his injury while Grayson became interim champion, giving them a ready-made program whenever Alexander receives clearance. No date has been announced, but MLP's Northern Rising on October 3 in Toronto would be a logical destination if Alexander is ready. The return is particularly meaningful considering Alexander has spoken about how disappointing it was to be unable to fulfill his responsibilities as champion after becoming the inaugural Canadian Champion following Scott D'Amore's relaunch of the promotion. On the WWE injury front, Logan Paul appears to be making progress from the torn triceps that required surgery after Saturday Night's Main Event in May. Paul recently visited Champion Sports Medicine in Birmingham, with Kevin Wilk saying he is looking good following surgery and eager to return to the ring. Paul himself has been more cautious, recently describing himself as still "very much injured" while saying that he is healing quickly and undergoing PRP treatment as part of the rehabilitation process. WWE has kept him involved on television during the recovery, while The Vision continued without him and Bron Breakker stepped into the tag team picture alongside Austin Theory. There is still no confirmed return date, but the latest update suggests Paul is progressing toward eventually getting back in the ring. Jim Johnston also believes the door to a WWE return is essentially closed. Johnston says he would happily compose wrestling themes again but believes Triple H views him as one of Vince McMahon's guys and has little interest in bringing him back. That is Johnston's interpretation rather than something Triple H has publicly confirmed, but it creates an interesting conversation about one of the most criticized aspects of WWE's current presentation. Johnston's greatest strength was creating music that immediately communicated who a wrestler was before they ever reached the ring. WWE does not necessarily need to turn its entire music department back over to Johnston, but completely ignoring someone responsible for so many instantly recognizable themes is worth discussing when modern entrance music continues to struggle to create that same connection. And finally, 31 years ago this week, Cactus Jack and Terry Funk produced one of the defining matches in the history of deathmatch wrestling at IWA Japan's Kawasaki Dream. Nearly 29,000 fans packed Kawasaki Stadium for the King of the Death Match tournament, with Funk and Cactus each surviving two violent matches before meeting in the final: a no-rope barbed-wire, exploding barbed-wire board and exploding-ring time-bomb deathmatch. Both men entered already beaten up, and what followed became the gold standard for the genre. The match worked because Funk and Foley could create emotion underneath all of the violence. The exploding boards delivered the spectacle, but the planned centerpiece of the match nearly became a disaster when the ring explosion at the ten-minute mark dramatically underdelivered. Instead of allowing the match to die with it, Funk and Cactus improvised. They went back to the remaining explosives and brought a ladder into the match, with Cactus eventually coming off it with an elbow before the closing sequence left both men tangled and destroyed in the wire. Cactus crawled over Funk for the pin and was crowned King of the Death Match. That victory meant considerably more than winning a tournament. Terry Funk was already one of wrestling's great legends and had rarely lost in Japan, while Cactus was still establishing what his career would become after leaving WCW. Foley has described the night as Funk effectively passing the torch to him, and the prestige from defeating Terry gave Cactus credibility that followed him long after Kawasaki. The match was messy, dangerous and even technically failed at the moment that was supposed to provide its biggest spectacle, but Funk and Foley turning that failure into something memorable is part of why it has endured. There have been crazier and more dangerous deathmatches since, but when you combine the atmosphere, violence, improvisation, emotional connection between the two men and what the victory ultimately meant for Mick Foley's career, Cactus Jack vs. Terry Funk remains one of the genre's defining matches. Episode 206 brings together one of wrestling's biggest crossover matches that never happened, Omega and Ospreay turning their decade-long rivalry personal before Wembley, Pat McAfee seemingly closing the door on WWE, Josh Alexander moving toward his comeback, Logan Paul continuing his recovery, Jim Johnston questioning whether WWE would ever welcome him back and a look back at the night Terry Funk helped make Cactus Jack the King of the Death Match.
The singles specialist era may have died this weekend. Dreambreakers, lineup decisions, and one jaw-dropping run of 17 straight points exposed what actually wins in MLP playoffs right now: rhythm, confidence, and clutch under pressure. Zane and Nico break down the wildest playoff weekend yet, including the LA Mad Drops' Dreambreaker collapse, Ben Johns' stunning 0-2 day and 17-point skid, and why Sam Parker's spot in the lineup became the center of a bigger debate about whether pure singles skill still matters in team pickleball. They also dig into Dallas Flash's surge, the trade that sent Tyra Black for Danni Townsend, and whether Dallas just proved they won the deal in real time.
The singles specialist era may have died this weekend. Dreambreakers, lineup decisions, and one jaw-dropping run of 17 straight points exposed what actually wins in MLP playoffs right now: rhythm, confidence, and clutch under pressure. Zane and Nico break down the wildest playoff weekend yet, including the LA Mad Drops' Dreambreaker collapse, Ben Johns' stunning 0-2 day and 17-point skid, and why Sam Parker's spot in the lineup became the center of a bigger debate about whether pure singles skill still matters in team pickleball. They also dig into Dallas Flash's surge, the trade that sent Tyra Black for Danni Townsend, and whether Dallas just proved they won the deal in real time.
Send us Fan MailThe MLP playoffs delivered some major surprises, and we're breaking down everything that happened in Newport.The Dallas Flash pulled off a massive upset over Ben Johns and the LA Mad Drops after looking like their season was falling apart just a few months ago. We break down how Dallas turned things around, J.W. Johnson's incredible run of form, LA's DreamBreaker decisions, and whether Ben Johns actually "quit" or Dallas simply outplayed them.We also break down Brooklyn's win over Columbus, Jackie Kawamoto's clutch performance, the Shock continuing to dominate, New Jersey surviving Palm Beach, and our predictions for the MLP semifinals and championship.Then we get into whether drafting singles specialists actually makes sense in MLP, Tyler's PPA Challenger experience in Seattle, a controversial new PPA side-switching rule, and some of the upcoming players making noise at Challenger events.Finally, we discuss the PPA's new World Pickleball Rankings system, why singles, mixed doubles and gender doubles are being combined into one ranking, and some of the strange results the new formula could create.Thanks for watching King of the Court! Subscribe for more pickleball news, analysis, opinions and behind-the-scenes stories.00:00 – Coming Up on KOTC00:46 – Welcome Back to King of the Court01:35 – Jimmy Goes Sleeveless 02:18 – Pickler Universe's New DFW Facility03:06 – Ranking the Best & Worst Airports06:04 – Dominator Pickleball07:34 – Jimmy Gets His New Montis Shoes09:00 – KOTC All Access Hits 140 Members09:49 – MLP Newport Playoff Recap10:45 – How Dallas Completely Turned Its Season Around12:21 – Why Dallas Didn't Blow Up the Team13:38 – The Moves That Changed Dallas' Season15:04 – Dallas vs. LA & the DreamBreaker Decision16:38 – Did LA Make a HUGE Mistake?17:19 – Ben Johns & Max Freeman Struggle18:14 – Did Ben Johns Actually Quit?19:04 – J.W. Johnson Is Playing Like the Best in the World20:44 – Dallas Pulls Off the Massive Upset21:32 – Brooklyn vs. Columbus24:09 – Brooklyn Advances25:17 – The Shock Absolutely DOMINATE26:44 – Fives vs. Palm Beach Recap27:31 – Tina Pisnik's INSANE ATP29:34 – Can Anyone Beat New Jersey in a DreamBreaker?30:17 – MLP Semifinal Predictions31:49 – Why Dallas Is the Team Nobody Wants to Face33:14 – Who Wins the 2026 MLP Championship?33:58 – Are Singles Specialists Worth It in MLP?35:32 – How MLP Draft Strategy Could Change39:10 – The Problem With Paying for Singles Specialists40:05 – Potential MLP Changes for 202740:50 – Tyler's Seattle Challenger Recap42:25 – PPA's NEW Side-Switching Rule43:06 – Why Players Don't Like the New Rule43:54 – PPA Challenger Men's Doubles Recap46:05 – Mixed Doubles Challenger Results47:40 – Challenger Women's Doubles49:27 – How Challengers Differ From the PPA Tour50:16 – PPA Australia + Upcoming Events51:08 – KOTC Live Podcast in North Carolina53:16 – Mark Wahlberg Shows Up at MLP54:43 – PPA's NEW World Pickleball Rankings56:10 – The New Ranking System Gets Weird57:57 – Major Ranking Surprises59:25 – Will the New Rankings Bring Singles Back?1:00:11 – Could Players Be Forced to Play Singles?1:01:31 – Final ThoughtsWebsite: https://www.tylerloong.com/ KOTC All Accesshttps://www.youtube.com/channel/UCDiH-sjthLCovD8i79-AkWg/joinCode “KOTC” for insane discounts at: https://www.clubpickleballmastermind.com/kotc KOTC Merch - Use “KOTC” kitchpickleball.comNEW KOTC DISCORD https://discord.com/invite/kNR65mBemfNEW KOTC CAMEOhttps://www.cameo.com/morekotcInstagram: Tyler's IG - @tyler.loong Jimmy's IG - @jimmymiller_pbKOTC IG - @morekingofthecourt Facebook: / tyler.loong --Support the show
[Verse 1]I was just a dreamer with a plan in my hand,Talking 'bout tomorrow, making people understand.Liquidity, blockchain, a future shining bright,But every promise made another sleepless night.They called me a leader,Said I looked the part,Nobody could seeWhat was breaking underneath my heart.[Pre-Chorus]One more month...One more deal...One more promise that would make it real...[Chorus]I kept the money moving,Just to keep the dream alive.Paying yesterday with tomorrow's sacrifice.Every smiling investor,Never saw the warning signs.Now all that's left are empty wallets...And these guilty eyes.[Verse 2]The mansion got bigger,The stage lights got bright.Charity dinners underneath the city lights.People trusted confidence,The watch, the suit, the name.Nobody stopped askingWhere the profits really came.The platform wasn't ready,MLP was gone.Still we kept believingWe could somehow carry on.[Pre-Chorus]Just one launch...One more fund...Surely everything would soon be overcome...[Chorus]I kept the money moving,Just to keep the dream alive.Paying yesterday with tomorrow's sacrifice.Every monthly paymentBought another little lie.Now all that's left are broken families...Wondering why.[Bridge]They say I wasn't alone...Maybe that's true.There were voices in the boardroom,There were people pulling too.But when the lights went dark,And the headlines filled the sky,The only name they remembered...Was mine.[Instrumental Break][Final Chorus]You can't build foreverOn money coming in.Every borrowed dollarHas a place it's been.More than a thousand voices,Two hundred fifty million gone.Justice doesn't move quickly...But it keeps moving on.[Outro]No software.No miracle.No billionaire walking through the door.Just victims...Waiting...For answers...Forevermore.Support the show
Zane screamed at Casey Diamond and the internet had thoughts. We're not letting it slide — Zane walks through exactly what happened in the Palm Beach playoff match, whether he regrets it, and where the line on screaming actually is (spoiler: he found it by crossing it). Then we read the meanest comments the internet had for him, rank pickleball's biggest beefs, debate the Memes of Pickleball controversy, break down every MLP playoff series and the seeding picks, and draft fast food items to build an MLP team. Stick around to the end. Cameron Boltes joins us to share the story of his son Solomon and the memorial pickleball courts being built in his honor in eastern North Carolina. It's the most important pickleball project in the country right now, donate or share if you can. Learn more about your ad choices. Visit megaphone.fm/adchoices
Send us Fan MailWe break down Zane Navratil's wild on-court outburst, the drama between Zane and the Palm Beach bench, and whether there's a double standard when it comes to screaming and trash talk in professional pickleball.We also recap the MLP playoff action, discuss Rachel Rohrabacher's lingering injury and post-match comments, and make our predictions for the next round.Plus, James Ignatowich had some surprising words for Tyler on another podcast, Memes of Pickleball sparks controversy with its latest posts, and we respond to the argument that the pickleball business is in serious trouble.00:00 – All Access 01:29 – Welcome to King of the Court03:33 – Pickler Universe05:41 – Dominator07:04 – Montis Pickleball09:24 – KOTC All Access10:10 – MLP Playoffs Recap11:57 – Zane Navratil's WILD Outburst13:38 – Zane vs. the Palm Beach Bench14:29 – The History Behind the Zane & Casey Diamond Beef15:54 – Chicago Slice Eliminated16:36 – Brooklyn vs. SoCal + Rachel Rohrabacher18:25 – SoCal Nearly Pulls Off the Upset19:59 – Rachel Rohrabacher's Injury Situation21:31 – Texas Ranchers Advance23:43 – Dallas Lights Go Out... Conspiracy?24:29 – MLP Quarterfinal Matchups25:21 – Who Should the New York Hustlers Pick?26:44 – Who Should LA Pick?31:16 – MLP Playoff Predictions32:19 – Memes of Pickleball Controversy34:38 – Did the Memes Go Too Far?38:07 – James Ignatowich Calls Out Tyler40:31 – Tyler Responds to Ignatowich41:19 – Is Tyler Polarizing?42:56 – Zane Doubles Down on Missing MLP for a Wedding45:11 – Is the Business of Pickleball in Trouble?47:02 – The Economics of Pickleball Facilities49:02 – Pickleball's REAL Average Age50:38 – Why Pickleball Isn't Going Anywhere51:23 – Club Pickleball Mastermind52:45 – Listener Questions53:24 – Dallas Lights-Out Conspiracy54:06 – MLP Salary Cap Explained54:49 – Why Isn't QD Dominating APP?56:14 – Is Zane Navratil Okay?58:26 – Vivian Glozman's Potential1:00:05 – Dallas Flash Lineup Decisions1:00:46 – Reacting to Zane's Freakout1:01:20 – How All Access Members Submit Questions1:02:18 – Did MLP's Playoff Format Create Blowouts?1:03:12 – Another Pickleball Tour War?1:04:11 – Are Pro Pickleball Salaries About to Crash?1:04:59 – Final Thoughts & Wrap-UpWebsite: https://www.tylerloong.com/ KOTC All Accesshttps://www.youtube.com/channel/UCDiH-sjthLCovD8i79-AkWg/joinCode “KOTC” for insane discounts at: https://www.clubpickleballmastermind.com/kotc Montis Pickleball shoesmontispickleball.com code KOTC More info on the Montis Pickleball tournament https://lader.sport/event/montis-openKOTC Merch - Use “KOTC” kitchpickleball.comNEW KOTC DISCORD https://discord.com/invite/kNR65mBemfNEW KOTC CAMEOhttps://www.cameo.com/morekotcInstagram: Tyler's IG - @tyler.loong Jimmy's IG - @jimmymiller_pbKOTC IG - @morekingofthecourt Facebook: / tyler.loong --Support the show
Zane and Nico are joined by California Black Bears star Zoey Weil to break down the best MLP event of the season — MLP Orlando. They relive the Dream Breaker for the ages between the Chicago Slice and Black Bears, where 13-year-old Elsie Hendershot saved match point and clinched the win to end California's season and keep Chicago's playoff hopes alive. Plus: the debate over player-GMs setting lineups, whether the Black Bears mortgaged their future for a 12-seed run, MLP's salary cap/floor future, Zane's wedding controversy, an MVP and Rookie of the Year debate, Guess My DUPR, and a Disney movie draft. Nico and Zane will be back later this week with a full MLP Playoffs preview — subscribe so you don't miss it.
Today's Post - https://bahnsen.co/4yUosr7 David Bahnsen reviews a “bizarre” July in which long-term yields rose, the Iran ceasefire/MOU collapsed, semiconductors fell sharply, and the yen hit multi-decade lows—yet the S&P 500 finished flat with improved breadth—and notes a strong early-August rally led by mega-cap tech while oil fell and energy dipped. He highlights massive hyperscaler capital expenditures and the key market questions around ROI, timing, financing, and systemic exposure. Bahnsen discusses shifting Iran headlines, policy items including the Todd Blanche AG nomination, the low odds of the Save Act and another reconciliation bill, Michigan's Senate primary dynamics, and a multi-state lawsuit over Section 301 tariff rationale. He covers Q2 real GDP at 1.5%, stronger July ISM manufacturing, elevated mortgage rates, Fed chair Warsh and balance-sheet effects, Treasury's reported yen buying, and midstream/MLP performance. 00:00 Welcome and Setup 00:23 July Market Recap 02:22 Monday Rally Snapshot 03:04 Big Tech Capex Questions 05:03 Iran Headlines and Oil 05:39 Washington Policy Update 07:50 GDP and ISM Readouts 09:01 Rates and Housing Impact 09:49 Fed Chair and Yen Move 12:45 Energy and Midstream Returns 13:10 Wrap Up and Next Episode 13:39 Disclosures and Disclaimers Links mentioned in this episode: DividendCafe.com TheBahnsenGroup.com
Watch the full episode on YouTube:We first covered Baseten last year when DeepSeek mania was at peak hype. Now they have raised a monster $13B round and become one of the new cohort of AI Infra decacorns that are (with Nvidia, Intel, and the semis complex) chief beneficiaries of the Inference Inflection. We return to Baseten at the peak of the 2026 edition of Open Weights debate. Ali has published a viral breakdown of Kimi K3:And since you last saw him, Philip has spoken at AI Engineer and written the definitive book on Inference Engineering spotted all over SF:Three years ago, inference engineering barely existed as a category.Today, it is one of the most critical disciplines in AI. Inference engineering inherently tackles a different question than standard model training: “How do you turn those weights from training into a product that is fast, reliable, and affordable at scale?” Focusing on these creates an entirely new optimization problem.In one recent GLM-5.2 experiment, quantizing more of the model actually preserved its benchmark quality while increasing throughput by 20%, because the errors introduced in different layers could cancel each other out.Inference is no longer just the final step after training. It is becoming its own engineering discipline, with its own research problems, infrastructure, and increasingly specialized roles.In this episode, Baseten's Philip Kiely and Ali Taha join swyx and Vibhu to explain what actually happens after a new open model is released and what it takes to turn “we generated a token” into a fast, reliable, production-ready API.We go deep on cache-aware routing, disaggregated prefill and decode, quantization, speculative decoding, KV-cache movement, model parallelism, GPU kernels, and the race to make frontier models up to 10× faster. Philip and Ali explain why inference optimizations can still produce gains of 20%, 100%, or even 200%; how quantization errors can cancel one another out; why identical weights can behave differently across clusters; and how Baseten grafted a Kimi vision encoder onto GLM-5.2 without changing the underlying language model.The conversation then expands beyond LLMs into NVIDIA Dynamo, mega kernels, Rubin, AI-specific chips, local inference, video generation, diffusion versus autoregressive models, and the enormous compute barrier to generating coherent long-form video. Finally, we explore the convergence of training and inference, continual learning through persistent KV cache, and the emerging loop where models help optimize the infrastructure that runs them.We discuss:* What happens when a 200,000-token request enters an inference system* Cache-aware routing and reusing previously computed KV cache* Why prefill and decode are increasingly handled by different GPUs* When dedicated deployments become cheaper and more reliable than shared APIs* How speculative decoding uses a smaller model to accelerate a larger one* Tool calling, structured outputs, and what LLMs actually do* What it takes to support a new open model on day zero* Grafting Kimi's vision encoder onto GLM-5.2* Retrofitting inefficient model layers with components from other architectures* Why models sometimes collapse into repeating the same token* How hardware, kernels, and race conditions create nondeterministic failures* Preserving model fidelity while making inference faster* How quantization errors can cancel each other out* Why inference optimizations still deliver gains of 20%, 100%, and 200%* How optimized serving can make a model up to 10× faster* NVIDIA Dynamo, KV-aware routing, and distributed model serving* Speculative decoding the speculative decoder* Why local AI is about making models less dumb while data-center AI is about making them less slow* Tensor, expert, and pipeline parallelism across GPUs* Hardware-aware model design, auto-tuning, and the case against mega kernels* Rubin and why inference is becoming a systems problem* Whether modern GPUs are evolving into programmable AI ASICs* Why enormous models like Kimi K3 require GB300-class hardware* Why open-source video generation still trails Veo, Kling, and other closed models* The quadratic attention bottleneck behind long-form AI video* Autoregressive video, real-time generation, and compounding quality drift* Why future video systems may combine autoregressive and diffusion architectures* Training for inference and inference for training* Continuous post-training, deployment, evaluation, and improvement loops* How GLM-5.2 helped optimize the kernels serving GLM-5.2 itself* Why faster networking could unlock dramatically faster decoding* Continual learning, KV-cache compaction, and persistent model memoryShow Notes* How to build a day-0 API for Kimi K3* 22580: From GPT2 to Kimi3, ExplainedPhilip Kiely* LinkedIn: https://www.linkedin.com/in/philipkiely* X: https://x.com/philipkiely* Inference Engineering: https://www.baseten.co/inference-engineering/Ali Taha* LinkedIn: https://www.linkedin.com/in/aliestaha/* X: https://x.com/waterloointernTimestamps00:00:00 Introduction and the 200K-Token Prompt00:03:18 Dedicated Deployments, Speculative Decoding, and Tool Calling00:11:26 Launching Production-Ready Open Models00:19:06 Model Retrofits, Failure Modes, and Nondeterminism00:28:22 Quantization and Canceling Errors00:32:15 The Race to 10× Faster Inference00:40:48 Dynamo, Speculation, and Local vs. Data-Center AI00:50:18 Model Parallelism, Auto-Tuning, and Mega Kernels01:00:55 Rubin, GPUs vs. ASICs, and Custom AI Chips01:10:03 Giant Models and the Limits of GPU Memory01:12:42 AI Video, Quadratic Attention, and Autoregressive Generation01:21:47 Audio, Images, and Diffusion Models01:27:32 Training, Self-Optimizing Models, and Continual Learning01:40:06 Closing ThoughtsTranscriptIntroduction: Baseten, Waterloo Intern, and Inference EngineeringSwyx [00:00:00]: Okay, we're here in the studio with Philip, old friend from Inference Engineering, the book, as well as Baseten and everything that you've done, you and I have done before, as well as Ali. Welcome.Ali [00:00:15]: Pleasure to meet you.Swyx [00:00:15]: Waterloo intern.Ali [00:00:16]: Waterloo intern, always.Swyx [00:00:17]: When did you get “Waterloo intern” as a handle?Ali [00:00:19]: As a handle? Oh.Ali [00:00:20]: I think the rebranding happened mid-March. When I saw it was open, I was like, “I have to take it. Up for grabs.”Philip [00:00:26]: The problem is that Ali is really good at his job and is not gonna be an intern much longer.Philip [00:00:30]: So we have to figure out who's gonna get the handle.Ali [00:00:33]: Well, I'll pass the torch over to the next intern.Swyx [00:00:34]: Oh, okay. It can be, like, you just pass it to another Waterloo grad.Ali [00:00:37]: To another Waterloo intern. No, bruh.Philip [00:00:39]: Yeah.Ali [00:00:39]: Intern.Swyx [00:00:40]: Intern, yeah.Ali [00:00:40]: And no.Philip [00:00:41]: You gotta get an intern from Waterloo.Ali [00:00:42]: Yeah, I've gotta get an intern from Waterloo.Swyx [00:00:44]: Right.Ali [00:00:44]: But they have to follow the path.Swyx [00:00:45]: Oh, it could, but it could come from Baseten, so it's like whoever Baseten gets from Waterloo.Ali [00:00:48]: Right.Swyx [00:00:49]: Has the title of Waterloo.Ali [00:00:50]: It stays in the ecosystem.Philip [00:00:51]: Exactly.Ali [00:00:52]: Halfway through the internship, you either get it or you're out.Philip [00:00:55]: You should also do, like, a big graduation ceremony where you change the handle.Ali [00:00:59]: Just say it.Philip [00:00:59]: For everybody.Swyx [00:01:00]: You guys are good at ceremonies, clearly. We had a nice launch of the book, very successful. But before we get into all that, I wanna start off with a fun question for you. Okay, you're an expert inference engineer. What happens when I send a long query, say two hundred thousand tokens into Baseten's inference? What's the process of query through GPU model routing, balancing, all that? What is all the stuff that we don't think about?Long Context Requests, KV Cache, and Cache-Aware RoutingPhilip [00:01:26]: With a long query specifically, the first thing that I'm gonna ask is, “Have you sent me this query before, or at least part of it?” and I really hope you have, because it's gonna be a lot easier for me and a lot cheaper for you. So the first thing that we're gonna look at is some cache-aware routing, where we're going to see, we probably have a number of instances, a number of replicas up serving whatever model you're hitting. We want to send this one to something with, number one, available prefill workers, and number two, ideally some cached input already there so that we can skip prefill on at least part of these two hundred thousand tokens. If you're doing two hundred thousand tokens, it's probably coding or a multi-turn agent or something where you would expect to have that cached. If you don't, we're gonna have to send it to a prefill worker. We've at least on certain models disaggregated prefill and decode, so you're going to have one set of GPUs that's solely going to process the input, create the KV cache, and get you your first token, and then that's going to be passed over to a separate set of GPUs, which is going to run decode. We're going to iteratively make those tokens. We're probably going to have some speculator model in front of that. I'm going to assume that you're doing coding, and because of that, our speculator model, which assumes you're doing coding, is gonna have a high draft token acceptance rate. If I'm wrong and you're asking me to summarize every Harry Potter book, it's gonna be slower. And then we stream that output to you and account for it, charge you, a couple of pennies and say, “Hey, would you like to send another one?”Swyx [00:03:04]: Except Baseten doesn't charge by pennies.Philip [00:03:07]: Well, yeah, we charge. I'm assuming that we're talking about the public model APIs. If you are setting up a dedicated deployment, then yeah, it's not pennies.Public APIs vs. Dedicated DeploymentsSwyx [00:03:18]: Yeah, one of the key differentiators when I was talking with Baseten initially was that people who want very high volume just need to rent by the box, ‘cause then it's up to you to figure out how to saturate the box.Ali [00:03:31]: And more often than not, it's, like, way cheaper if you're pushing, like, millions of tokens per hour, if you just pay per hour instead of pay per token.Philip [00:03:37]: Yeah, they do. I think that we've increasingly seen a lot of demand for the pay per token APIs, just because everyone wants to try open models, and then once they find a use case that's really sticky, then they move over to dedicated.Swyx [00:03:51]: Is there a best practice on when it's time to swap over?Philip [00:03:54]: Couple reasons. Yeah, reliability, that's a big one, right?Ali [00:03:57]: Like, if they have a very specific use case, they want you to train something specifically for them, like they want their own spec dec, for instance, for their own traffic.Swyx [00:04:04]: Spec dec is speculative decoding.Speculative Decoding and Custom SpeculatorsAli [00:04:05]: Speculative decoding, yeah.Swyx [00:04:07]: You have to explain.Ali [00:04:07]: Sorry. Like, speculative decoding is like, if you have a huge model, right? And so the model is going to be generating one token at a time every single turn, every single forward pass. So we attach, like, this little, like, parasite, like this layer that goes on top of the model, and this model just has to predict. It does three very fast autoregressive forward passes, and it will predict, like, three certain tokens, and then you do one forward stage over the entire original model in order to see if those predictions were correct or not, and then you accept them or you reject them. Now, this draft model is traffic specific, so if you, like, Philip said, if you're summarizing Harry Potter books, I can train exclusively that draft model on Harry Potter books, and I can guarantee you that I'm gonna accept the three tokens every single time. And so with that case, I increase your decode speed. I wouldn't be able to provide this to you if you're a shared endpointSwyx [00:04:53]: YeahAli [00:04:53]: ‘cause I have no idea if you're doing Harry Potter, if you're doing coding, if you're doing English. We don't know. Also, there was a thing in the book that mentioned that if they really cared about a specific threshold, chapter four, I think. Do you remember that?Philip [00:05:06]: Yeah. The things that you can do is you can set a specific, like, batch sizing, a specific, like, parallelism strategy if you're trying to optimize for, like, throughput versus latency. You can. Maybe a NVFP4 quant doesn't pass your benchmarks and you wanna run a model at higher precision, you could do that. There's just a bunch of reasons why you might wanna have your own endpoint and the biggest one, of course, just being, like, you don't have to deal with someone else doing a hundred million tokens of benchmarking traffic at the endpoint when you happen to be trying to serve your users.Swyx [00:05:40]: Yeah. I think one thing that is. That is a classic journey. Like, it's people is asking the, what happens when you type Google into the browser. Tool calling, is that just, you're generating JSON or is there more complication beyond that?Tool Calling, JSON, and Structured OutputsAli [00:05:58]: Certain customers that we have, they have their own post-trained models, and so they demand a tool calling that's not just, like parse a file or go find the weather. It's something that's very specific and you have to do post-training on this. And if the post-training on the model is not good or if the quantization after the post-training to get the inference to be fast, the model will struggle reading the JSON file and reading the tool calling. But it doesn't require its own like sandbox. It's not like it's going to use that tool calling to like escape a sandbox or like it doesn't have to be contained. It can just be a normal dedicated deployment. The challenge with tool calling more and more seems to be that the companies want certain tool calling which is a very sensitive thing to train. And because you're dealing with all of the JSON outputs, if it doesn't like close the end of the request in a very certain manner, you end up with a model that did the tool calling and like the thinking and so as a result of that, it didn't see the result and just hallucinated the result as it decoded. That seems to be the most challenging thing with tool calling, not really the sandboxes model.Philip [00:06:56]: Yeah, that's a challenge on the training side and then on the inference side, there's work that you can do to scope the possible output. So we published this at this point close to two years ago, the solution to this problem which is you make a state machine and you use that to constrain the output to a specific format. So this is the structured output problem. If you remember backSwyx [00:07:27]: Yeah, the specific grammar is,Philip [00:07:29]: Yeah, exactlySwyx [00:07:30]: GML had this thing.Philip [00:07:31]: Yeah. So it's like the old-school “make sure this is only JSON”, return only JSON orSwyx [00:07:38]: YeahPhilip [00:07:38]: Grandma's gonna die type of prompts.Swyx [00:07:39]: Is it BNF grammar? At some point OpenAI had released a thing that was like, yeah, if you want to constrain your output, write BNF grammar, back as NOR.Philip [00:07:47]: In our inference system, it's just a specified output format. And you get the guarantee that your output's gonna be structured along that format. And so applying that to tool calls can like help cut down on. You can still call the wrong tool or call no tool. It doesn't solve the certainty problem but it at least solves the output structuring problemSwyx [00:08:10]: YeahPhilip [00:08:10]: Within tool calls.Swyx [00:08:12]: And MCP is just another form of tool, right.Philip [00:08:14]: Yeah, exactly.Swyx [00:08:15]: As far as there's no special thing there.Philip [00:08:16]: The thing I'm always like explaining to people is the LLM is not capable of doing anything. It's only capable of making suggestions of what to do and then if those suggestions are formatted in a certain way and applied to a system that knows what to do with them, then an action occurs.Swyx [00:08:32]: Yeah. Part of the fun stuff is, this is solved outside of tool calling too. Like in an agent loop if the output is not correct or you're right, like reasoning, tool calling was done in the reasoning trace, just be like, “Oh, I don't know what to do. Let me just try again.” And it might get there after a few tries. And on your point of training, sometimes this is harder in smaller models, so you don't have the same exact quality outputAli [00:08:56]: Right.Swyx [00:08:57]: When you just swap from a big model, right?Ali [00:08:59]: Yeah. I will say that, before, I think we need to go back to inference engineering proper.Ali [00:09:04]: But, I had expected that something would replace JSON because it's hard to stream JSON ‘cause JSON must be complete and you must have open and close brackets and everything. So it's hard to parse something or validate something while it's being streamed. So people invented all sorts of things that are like, I forget the name of some of these alternatives, but it's something like TOML, something like YAML. But JSON seems to be dominant still.Philip [00:09:30]: The JSON outputs aren't that long, right? Like you could have a long-- ‘cause tool calls also contain the arguments in them and perhaps for a certain tool you might pass like a very long argument. But my impression of the median tool call is that it's a relatively small number of tokens, right? So I would expect that speculators are generally fairly good at something as formatted as JSON. And so you would have like a pretty fast decode step there and that the streaming wouldn't be as valuable, but maybe I'm wrong about that.Ali [00:10:02]: I think you're also bounded by the software or that the model is gonna integrate with if the software is built with JSON for the tool calls or if the company that you'- if your customer says that this is how our software works and our tools are interfaced with JSON, you can ask them to like, change their software and say like, “Yeah, this is gonna be better for the model.” but like with the right training shouldn't be that much of a difference. Also more profitable if it outputs more tokens probably.Swyx [00:10:25]: Depends on your business model.Swyx [00:10:27]: It really depends. But I will say that, as a writer with like experience a lot with generated output, I do try to move from text to JSON text which is very long JSON, right? Like there's paragraphs in every field because I'm trying to structure it, right?Philip [00:10:44]: Right.Swyx [00:10:44]: I want you to first make factual statements, then make opinions then make bullet point summaries, have dates, have entity references have your sources for references, all these things. Anyway, so these are things that like I think people who really experiment with structural output have to really care about. But, let's, let's recurse up the stack a little bit. Before we started recording, you mentioned something really cool, which is that there's a lot of engineering that-- inference engineering that goes on when a new model provider releases a new model, right? So let's call it GLM-5.2, Kimi K3. I had previously assumed, especially if it's like, well, GLM 5 to 5.1 to GLM-5.2, like that you've supported them before. Is it that much work?What It Takes to Support a New Open ModelAli [00:11:26]: It's a lot of work.Swyx [00:11:28]: Yeah. Okay. So like, a lot of people, all you guys, right whenever a new model launch like, people rush to say like, “Oh, Hugging Face supports this, Fireworks supports this, Spacetime supports this,” and I'm like, “Yeah, of course we support it.” But what goes into that? What goes intoPhilip [00:11:40]: I think it's more than just support it too, right? It benefits the consumer a lot. Like I think it was with Kimi K2.5 or GLM-5.2 the latest, there was an inference war, right? X provider is at 90 tokens a second. The next day we're at 150. The nextSwyx [00:11:55]: I kinda kicked that off with the GLM-5.2.Swyx [00:11:58]: I wrote a Twitter article about. It got like half a million views,Ali [00:12:02]: Based on being numberSwyx [00:12:03]: YeahAli [00:12:04]: Or it's for something else.Swyx [00:12:05]: Yeah. Which,Ali [00:12:06]: Oh my GodSwyx [00:12:07]: Which then got everyone really excited about, hey, how can we, bend tracks a little bit further and,Philip [00:12:14]: There's a difference between support the model, as in I can make a token out of this model, and support a model, as in I have a production-ready API from this model.Philip [00:12:26]: Getting to the point of I can make a token out of this model is not that hard because generally the, open source inference engines, vLLM, SGLang of the world oftentimes even receive weights ahead of time, maintainers do, or the people making the model merge PRs to ensure support. So you generally can, just get it working on the standard open source stack without too much pain in most cases. The challenge is, every inference company is gonna have own proprietary stack. Some open source components, some in-house stuff. And for any arbitrary model, there's going to be some new stuff. Sometimes you get lucky, like K, two five to two six was, like, pretty similar.Quantization, Speculators, and Production ReadinessAli [00:13:16]: Yeah. It was pure continued post-trainingPhilip [00:13:18]: YeahAli [00:13:18]: If I remember correctly.Philip [00:13:19]: Even in those cases, there's still stuff you have to do. You have to redo the quantization work. You're taking the model from. Generally, these models are not released in NVFP4, and we want them to be in NVFP4 for maximum Blackwell compatibility. So we have to perform that quantization, and, calibrate the quantization to make sure that we're not causing any regression in the model's intelligence. And then we also have to train the speculator, as we've talked about. Generally, we have. We have ZDR, zero data retention on our model APIs, so we don't know exactly the traffic that people are sending us, but we know what's popular. We know that coding use cases are popular. We know that agents, agentic use cases are popular. So we can get public data sets that are representative of that traffic and train general speculators. Now, with speculators today, you need to train the speculator using the base model itself because you're getting hidden states out of the model from running inference on these specific prompts, and that is the training data you use to create the speculator. So there's that process which you need the real model weights for. And then there's of course just the process of, standing up all the infrastructure behind it, loading all this stuff, testing it. And then when there's a new model with a newer architecture, I think that, like, the DeepSeek models tend to be the most challenging as they have, like, the most novel architectural stuff going on, model after model. But every new model has something. Kimi K2 had. Oh, sorry, GLM-5.2 hadAli [00:14:53]: Sparse attention.Philip [00:14:54]: Yeah,Ali [00:14:54]: YeahPhilip [00:14:54]: the DSA.Ali [00:14:55]: Right. Which is brought from DeepSeek.Philip [00:14:57]: Yeah. AndAli [00:14:59]: So you can copy-paste then?Philip [00:15:01]: It kindAli [00:15:01]: I don't know how this works.Philip [00:15:02]: So, like we had to, like, build support for that into our runtime. And you're right, like it is really interesting the way that all of these open source labs borrow from each other. For example, like GLM-5.2 doesn't have vision. So something that, Haley, a guy on our team, if we could take a look at this, he, like, grafted the Kimi vision encoder onto GLM-5.2.Retrofitting Vision into GLM-5.2Ali [00:15:27]: We'll be training the projector.Philip [00:15:28]: Exactly. So if you think about, like, the encoder, there's the encoder, which is the part that looks at the image and turns it into latent information, and then there's the projector which likeAli [00:15:38]: You can say latent space. It's okay.Philip [00:15:41]: And then there's the projector that maps it onto, the model itself, and then there's the model weights. You don't wanna mess with the model weights because you run a chance of making the model dumber at something else for the purpose of giving it vision. So instead, Haley started with just a projector, which is only a handful of millions of parameters.Ali [00:16:02]: That would be, yeah.Philip [00:16:02]: Yeah.Ali [00:16:03]: Can you show the training one?Ali [00:16:04]: Like the way it groksPhilip [00:16:05]: YeahAli [00:16:06]: Very interesting.Philip [00:16:06]: And maybeAli [00:16:07]: That right therePhilip [00:16:07]: Maybe Ali, you should take it from here. You've got a betterAli [00:16:10]: Ooh, double the sandPhilip [00:16:11]: Understanding of this than I do.Ali [00:16:11]: Yeah. You can see, like, he. The way he trained this is really cool. At the beginning, he was training it using just like, “Here's a picture of a mountain. Can you describe what's in this mountain?” And that caused it just like the first, learning walls. Like here you can see this all we're trying to teach it is to translate the encoded. Like it's already taken the encoder from Kimi K. It's taken the image. It'Philip [00:16:31]: Yeah. FrozenAli [00:16:31]: FrozenPhilip [00:16:32]: With adapter.Ali [00:16:32]: Exactly.Philip [00:16:33]: Yeah.Ali [00:16:33]: So the brain is frozen and the eyes are frozen. It's just we're tryingPhilip [00:16:37]: AlignAli [00:16:38]: Interconnect between the eye and the brain, right? So the projector. And so you take the tokens and then he's like, “Oh, can you describe what's in this image?” And he's like, “Oh, it's a mountain,” or it's a person or it's a human, whatever the case is. But that didn't cause complete understanding. So he changed it such that every image was associated with a data set of questions. Like, does this image have a white male? Does this image have birds in the top corner? Does this image have a scientist in it? All of that stuff. And it would have to answer questions correctly. And using not just training on describing an image, but being able to answer question, another question, answer over time. Like you can see the grokking, which is like genuinely insane, that retrofitting vision into a large LLM can learn to that extent. And even for images that it doesn't perform well on, for instance, if you ask it a picture of like Stephen Hawking, “Who is this?” Maybe it doesn't get it, but it will say something like, “This is Albert Einstein.” Like it still understandsPhilip [00:17:25]: Close enoughAli [00:17:26]: That this is a scientist who is a man who has, some significant achievements, all that stuff. So that's like really cool.Philip [00:17:32]: Yeah. So, we've covered Hao Tian before, who the author of the LLaVA paper that did this, a while ago. And I think that's very foundational work for anyone who hasn't done vision work before.Ali [00:17:41]: Same with the CLIP and MetaCLIP, where you go from just captioning to building out questionsPhilip [00:17:47]: RightAli [00:17:47]: Off the image and how much better you can get performance.Philip [00:17:50]: Right. Right. Right. Yeah. But what's, what's so exciting about this is if you look at a model like this. Now, this is a little bit more of a research project. It's not. It got to 56% on MMLU Pro, I think. So not quite frontier. But if you're running this model, you haven't suffered any loss on your GLM-5.2 quality. If you don't have an image, it'll just behave exactly the way it used to. And ultimatelyAli [00:18:14]: Which in the inference code you literally do not include the other part, right?Philip [00:18:18]: Yeah. You would just skip the encoder if you don't have an image input.Ali [00:18:22]: Okay.Philip [00:18:22]: Just confirming.Philip [00:18:23]: YeahAli [00:18:23]: Does it affect a lot on the overall inference side? Like you're not adding much, you're adding a very small vision encoder. These are typically likePhilip [00:18:30]: They're super fineAli [00:18:31]: Less than a billion parameters, right?Philip [00:18:32]: Yeah. It's, - There's a little bit less standardization among vision encodersSwyx [00:18:37]: YeahPhilip [00:18:37]: So the support matrix can be a little bit, sparser. But overall, yeah, it's a pretty, it's a pretty minor component of the overall system. And ultimately what you get out of the system is all of a sudden you have Kimi Vision, GLM weights, and DeepSeek attention all in one model.Open Source Model Grafting and Franken-MergesPhilip [00:18:56]: And that's, I think, a lot of the power and beauty of open source, is that you can take all of these different components and combine them together into a system that's better than anyoneSwyx [00:19:05]: YeahPhilip [00:19:05]: Can be individually.Swyx [00:19:06]: People used to say that you would also do Franken-merges where you would take likePhilip [00:19:10]: YeahSwyx [00:19:10]: Layers from each model.Swyx [00:19:11]: Does anyone do that anymore?Ali [00:19:13]: Well, to your point previously when you were mentioning like, the work that goes into supporting a model when it first comes out, like GLM-5.2 or MiniMax M3 or whatever the case is. Sometimes you do have to like, you do have to switch out some things. Like, for instance, the MiniMax M3 head uses full attention, and with full attention you end up with this like insane bottleneck in spec dec ‘cause you're doing auto-regressive token generation for three tokens, and you're doing this like N squared over all of the tokens that are in your sequence. Your KV cache is like very large because it's not sparse, it's not top K. So we find it better to like, okay, we're gonna replace this, we're gonna replace this layer with a layer from another model that's using like GQA, for instance. And then just with the right training, you can get it to have the same acceptance rate. So it is very possible to retrofit layers from other models and very much needed. If a layer is like inefficient, the training just becomes the challenge, like how do you ensure that you train it properly? Which again to your earlier point is like the mesh between training and inference. As in like you need very good training in order to do fast inference. That's like, I feel like more and more becoming true.Swyx [00:20:21]: Yeah. Anything else on the support side when you say like get it to fully production ready?Loop Detection, Race Conditions, and Non-DeterminismPhilip [00:20:26]: Yeah. I think that there's also a question of just, we can test a model to a pretty extensive degree, but we're trying to get it out quickly and then you see a bunch of other people test it and you get interesting results. There was an issue with, GLM briefly where we had some like mode collapses where it would just output the same token over and over again for certain prompts on certain temperatures. Like once you expose an endpoint to the real world, there's going to be, so many more varieties of things given to it that you're able to, discover and patch things. So it's not just a, day zero process, it's then like for the first week, for the first month, if a model remains popular, like how do you both fix bugs and then continue to push the envelope on performance?Ali [00:21:21]: What do you mean you don't want your model outputting S?Swyx [00:21:24]: Is there loop detection on that stuff, by the way? It still happens like quite a lot, which is surprising.Ali [00:21:30]: We have like we, in our endpoint, like if a model was to output the same token like four plus times, we just cut the generation. We say like, “Oh, sorry, this-- Like try again,” or like we will reprocess the request. ‘Cause we know then, like if it, like if, yeah, it's four times the same token, it's probably collapsed.Swyx [00:21:45]: Yeah. Is there a way to opt out in case I really want that?Ali [00:21:48]: You want that?Ali [00:21:50]: I think there's a way that we have to handle it. I'm not exactly certain, but I feel like in certain models, like when they output something like you can imagine, like a table for instance, and so they want, they wanna draw like 12 dashes and 12 dashes. Yeah, I think there's a way for that to happen. I think we only do it on certain tokens. Like we exclude certain special characters.Swyx [00:22:07]: Yeah.Ali [00:22:07]: So we only do it on like certain like S is the most common almost. GLM-5.2Swyx [00:22:11]: OhAli [00:22:11]: And I think it was DSV 4 as well. Like you'd just have like looping issues where like you literallySwyx [00:22:17]: ItAli [00:22:17]: Just have like S.Swyx [00:22:18]: Yeah. Is there a special, something special about S? No, just randomlyAli [00:22:21]: It just seems to be the one token involved.Swyx [00:22:23]: Yeah. And it'Philip [00:22:24]: Is thereSwyx [00:22:24]: And it's only temperature 0Ali [00:22:27]: NoSwyx [00:22:27]: Even at other temperaturesAli [00:22:27]: Even at like 0.9 or whatever, it will still, it will still collapse.Swyx [00:22:30]: That's weird, right?Ali [00:22:30]: It's, it is an inference problem to be honest, like a software problem. Like oftentimes, the image you run will-- like NVIDIA will release an image for instance, and if we will upstream the changes from their latest TensorRT-LLM image into our stack, we'll find that it fixes it. Or oftentimes this will only happen in an inference engine that you're using like SGLang. But if you were to switch to vLLM, that isn't the case. So it seems to be like an extremely like deterministic software issue and not really a model issue. It's not like a weights problem. Like I'- we'll say like, “Oh, it's a problem with the quant. We did PTQ wrong,” right? But that isn't, that doesn't make sense because the same weights used with a different inference engine does not repeat the problem. And sometimes it's, the kernels that are being used in the backend have like these very subtle sometimes race conditions, where if you were to use this model hosted on one cluster, you will never get this problem.Swyx [00:23:19]: Oh my God.Ali [00:23:19]: But if you host it on a different cluster, you will. And the reason is the KV cache transfer from a node to node in that one cluster is using a slower interconnect than the node to node in another cluster. So that exposes the race, whereas in another cluster it doesn't. So then you end up just like, okay, this model is not gonna be hosted on this cluster. We're gonna host it on, another cluster because that cluster exposed that problem. But then it ends up with like, okay, is it the software? Is it the model weights or is it the hardware?Swyx [00:23:42]: There is a thing about this with temperature 0 still not being deterministic, right?Ali [00:23:46]: Right.Swyx [00:23:46]: Mostly because of hardware. Even at temperature 0 same model, you won't always get the same output.Swyx [00:23:52]: Even-- But I'm surprised by the race condition one because, I thought PyTorch was a graph that like guarantees that you at least, execute things in the right order.Ali [00:24:02]: Well, yeah, true. Like I'm not, I'm not saying that there is. Like well, you have things like PTL optimizations where like you can start a kernel before the end of the previous kernel, and that's like ‘cause you want to do that because there'sSwyx [00:24:12]: It's like pipeliningAli [00:24:12]: Expense. Exactly.Swyx [00:24:13]: Yeah.Ali [00:24:13]: But it'- But you don't do it cleanly. Like you overlap a little bit of the execution. No, it is very possible that the kernel itself, like that one block that is supposed to be running in this instance of time, that kernel itself has a race condition. For instance, like a missing barrier. Like often if you're designing a kernel and you want it to make it to be very fast, if you don't test it extensively, you'll, you'll have certain threads access data points from registers before they've been written to by other threadsSwyx [00:24:36]: YeahAli [00:24:36]: For example, because like your barrier is wrong or your synchronization was wrong. But yeah, like the testing itself is very difficult in those like, andSwyx [00:24:42]: And there's no like borrow checkerAli [00:24:45]: What does that mean?Swyx [00:24:46]: Like Rust. Like the. If you're trying to have like memory safety It sounds like a comparable problem.Ali [00:24:52]: Well, yes, but you're working in CUDA, right, NVIDIA GPUs. Like- You just need a higher level language like modular Maybe that's what modular is supposed to do. I don't know.Quantization Quality and Vendor FidelityVibhu [00:25:00]: How do you see keeping quality of the model? So you talked about all these steps of, okay, you gotta do quantization, train your own speculative decoderAli [00:25:07]: RightVibhu [00:25:07]: Run on different hardware. Looking at other model providers, okay, you kicked off a inference speed race on the consumer end. What goes into keeping quality the same across them, right? Sure, you can run benchmarksAli [00:25:22]: YeahVibhu [00:25:22]: But, like, how do you determine how much quantization are there standards? What goes intoPhilip [00:25:27]: There's a few things on quality. Most inference optimizations are lossless. KV caching, for example. You are just recomputing or preventing recomputing the same values. Speculation, of course, if a draft token is wrong, it gets rejected. The main lossy optimization is quantization. And that really comes down to, number one, data format, number two, which parts of the model you choose to quantize, which layers, and number three, like doing a lot of calibration on the quantized weights, to ensure that you're preserving all the outliers. There's other tricks that you can do, though. A big one is long context, ‘cause one thing you asked at, right at the beginning is, “Oh, what's gonna happen if I send a 200,000 token request in?” So with a long input sequence, you need to, store a lot more information. You need to process a lot more tokens. And so even if a model has a context of a certain length, you might, as an inference provider, choose to build an API with a shorter context length, and of course a full length one as well. Because if someone doesn't need the full million token context, for example, you can get them better performance. I don't know if that's exactly like quality of the model. The way that I think about quality is to what degree are we faithfully serving the original model? If you think of a golden implementation of a model that performs exactly the way the model is designed to perform, I think of quality as how close are we getting to that, 100% fidelity of the model.Philip [00:27:13]: You can also, of course, think about quality from the training side and how do you push yourself past 100%. But when I think about purely inference optimizations, it's getting faster while staying as close to that 100% fidelity mark as possible. And certainly our standard internally is that, like you should not be able to tell the difference between our API and a, official API. I think Kimi in particular does a good job of vendor benchmarking hereAli [00:27:41]: YesPhilip [00:27:41]: Where they haveAli [00:27:42]: They released an actual vendor benchmark.Philip [00:27:43]: Exactly, yeah.Ali [00:27:44]: ‘Cause they accused, some people, Amazon? There was some provider that was not doing very well on Kimi's benchmark.Philip [00:27:50]: Yeah.Philip [00:27:51]: So, with Reflect we probablyVibhu [00:27:52]: This was a long time ago, right?Philip [00:27:54]: No.Ali [00:27:54]: Yeah, like threeVibhu [00:27:55]: They alsoAli [00:27:55]: Four, five months agoVibhu [00:27:57]: This also happened with, I don't remember which model, but they pulled out quite a few, and then they started a whole chart about this. It might have beenPhilip [00:28:03]: Kimi Vendor Verifier.Ali [00:28:04]: Yeah.Philip [00:28:05]: Yeah.Ali [00:28:05]: Yeah, ‘cause you, ‘cause you'd be pissed, right? Like if you'Philip [00:28:07]: Yeah.Ali [00:28:07]: If like if I'm a consumer and I'm using like Amazon's endpoint for instance, and I've used Kimi and I'm like, “Oh my God, like this is bad,” I'm not gonna say, “Oh, Amazon quantized the model in a bad way.” I'm gonna say, “Oh, Kimi sucks.” Right?Philip [00:28:17]: Yeah.Ali [00:28:17]: So it seems like that makes sense.Philip [00:28:19]: Yeah, they care. They care.Vibhu [00:28:21]: Justifiably.Ali [00:28:21]: Yeah, justifiably.Vibhu [00:28:22]: This is probably a stupid question, but just checking, has anything improved from main quantization?Philip [00:28:28]: Yeah.Vibhu [00:28:28]: Like, is quantization always strictly worse?Ali [00:28:30]: Well technicallyVibhu [00:28:32]: NoAli [00:28:32]: It's a lossy. QuantizationPhilip [00:28:33]: YeahAli [00:28:33]: Is a lossy, it's a lossy implementation.Philip [00:28:36]: Speed improvesVibhu [00:28:36]: Speed improves.Ali [00:28:37]: It the number, likeVibhu [00:28:38]: No, I' always look for inverse scaling laws.Philip [00:28:40]: Yeah.Ali [00:28:40]: Yeah.Vibhu [00:28:40]: This is something I learned from Noam Brown, where like things that normally act in one direction sometimes do.Philip [00:28:45]: Well, technically when you run a benchmark, because these models are deterministic, sometimes your,Ali [00:28:52]: YeahPhilip [00:28:52]: NVFP4 quant is like, two basis points higher than yourAli [00:28:56]: No, it's noise. It's noise.Philip [00:28:57]: Yeah, exactly. I'm like, yeah, it's, it's within. That's why I always say within margin of error.Philip [00:29:01]: And I stopped saying that because everyone assumes that what is, well, within some margin of error, we're barely inside of that to the worst, so we're saying. But yeah, sometimes it's just like, gives you a higher output score. But like Ali said, that's noise. To my knowledge, you're not necessarily making the results better. You're just trying to, again, like keep your fidelity as close to 100% to the original model.Layer Selection, KL Divergence, and Better QuantizationAli [00:29:27]: There is, to your point, research that we did on MP. I don't know if you are able to pullPhilip [00:29:31]: YeahAli [00:29:32]: A tweet we did. One of our research interns, Joshua, I think it's a tweet on how we have 20% better quantized GLM-5.2 than NVIDIA. Essentially what we found throughout like this month research is, okay, quantization is a lossy. It's. You're compressing the data from, occupying 16 bits to occupying, four bits, for instance. And so you're losing some information, and you're trying to minimize that. And so when I say that I'm gonna quantize the model, my job becomes how do I find the layers that I can quantize, and how to find the layers to not. For instance, with image models, I don't quantize modulation layers, and I don't quantize out projections because those two are. Like out projection is what you see as the user. Modulation is what the model sees or understands. Right, exactly. And so to his paper, do you have the. It doesn't have the. Yeah. It's a long paper. I don't know if I can findVibhu [00:30:25]: If there's a part to search or it's probably in the thread.Ali [00:30:28]: It's probably in the thread.Vibhu [00:30:29]: Yeah.Ali [00:30:29]: But the long and the short is it is very possible that quantizing more of the model makes the results. Like if I have a model that I quantize layers one, five, and 10, and another model where I only quantize layers one and It is possible that the model in which I quantized more information is going to perform better because the quantization errors have canceled out. And so what Joshua showed in his mathematical proof where he had like a verifier in, is that you can predict which layers are going to have quantization errors that will cancel out with each other, and you choose to quantize those layers. And so the result of doing this mathematical quantization is you end up with a model that's 20% more quantized than another provider, so you get 20% more throughput of it because there's more layers than running an NVFP4, and your quality is better than that other quant because the layers that you chose to quantize have their errors cancel out, like one layer skewed to the right one layer skewed to the left, one layer skewed to the right. Your final logits distribution is more similar to the original distribution of the model, so you have better fidelity. And so the way we proved this was with KL divergence. So instead of just scoring on the benchmarks, we scored the KL divergence between the logit distribution of the quantized model and the logit distribution of the original full precision model, and we showed that with this technique we get. If your probability distribution on the logits which token it wants to select is more of the same as the original model, you're probably gonna end up staying true to the original model. So yeah, so it seems like previously before this, it seemed like the industry was, well, the more you quantize, the worse it's gonna be, ‘cause the more loss you introduce. That's not exactly, not necessarily true. So yeah, doesn't improve it, but can cancel out.Philip [00:31:57]: I think it might be this, but reminds me a good bit about pruning where you can prune off certain layers.Philip [00:32:03]: But very interesting. Didn't know this was a whole paper you guys put out.Ali [00:32:06]: It's. Fun fact, it was originally 72 pages, this paper, and then we decidedPhilip [00:32:11]: WowAli [00:32:11]: We can't tell. We couldn't release it. So it's now 45.Swyx [00:32:15]: Still 39 pages, so very substantive. We talked about evals and all these things and, like what's possible in terms of speedup? Like it's like probably like the numberInference Speedups and BenchmarkingSwyx [00:32:25]: Thing that people do wanna care about, and it's something that you wrote about in your post. Like official API is 70 tokens per second, and you push it up to 90. Is that like a normal thing?Philip [00:32:36]: So what's cool about working in inference, the reason that I think inference is going to be a useful place to do engineering for a long time, is that if you look at highly optimized domains like, say, finance, if you're in finance, you measure how much better you got in basis points. It's like, “Oh, I got five basis points better, like twentieth of 1% better,” that's huge news because everything is so optimized. When we publish optimizations, it's 20%, it's 100% it's 200%. So there's still probably like a lot further to go, honestly. Like you'll, you'll know that inference is pretty much solved when researchers start publishing about how they got 1% faster at something.Swyx [00:33:19]: Which by the way, because I am from the finance background, in the ‘70s, that was the margin at the time. When you did quantitative finance research, you would findAli [00:33:27]: And like 20%, tens of percent.Swyx [00:33:29]: That's. Yes.Philip [00:33:29]: Yeah.Swyx [00:33:30]: And now it'Philip [00:33:31]: Tiny fractionsSwyx [00:33:32]: For those people interested, look up Andrew Lo's paper. He had a really interesting illustration of quant, stat arb, distribution, narrowing down from like those kinds of 20% differences in the ‘70s, down to nothing today, which is very cool.Philip [00:33:48]: Exactly, and we're at the beginning of the same type of thing. Now benchmarking is hard. I think anyone will tell you that, and benchmarking provider speeds is hard because there's so many variables that go into it. What hardware are you using? How much load do you have on the system? What's the exact nature of the prompts and input and output sequence lengths? All that stuff. But overall, when you start stacking these improvements, you're looking at multiples. You can look at it. The most common form, of course, is TPS, tokens per second, which is bad naming by us in the industry, ‘cause there's two tokens per second. There's tokens per second, the throughput number, and the latency number.Ali [00:34:31]: TTMT, yeah.Philip [00:34:32]: Like total tokens per second out of the, out of the GPU as a throughput number. Most people only care about tokens per second as the latency number, which we should call ITL, intertoken latency, but we don't.Philip [00:34:44]: Anyway, so you can imagine a standard API without many optimizations for a 1 trillion parameter model operating somewhere in the 30 to 50 tokens per second range for reasonable traffic profile. And we generally see the goal of, pushing to 10X that. But, not necessarily day zero, but by stacking enough optimizations, if you have, say like four optimizations, each of which doubles performance. Or sorry, three optimizations, each of which doubles performance, then you stack that up, that's an 8X gain. That's the order of magnitude that we're working with in this space. We're trying to make things substantially faster, not just go from like 70 to 90.Swyx [00:35:38]: Are you saying you've. You have done that?Philip [00:35:40]: So let's say you have as a reasonable baseline, 30 or 40 tokens per second. You can achieve 10X that. So like on GLM-5.2, if you run it unquantized, perhaps on H100s even, and you're just using an off-the-shelf inference engine with no particular optimizations, no speculator, nothing extra around like KV routing, no disaggregation, you're, you're probably, yeah, looking at that like 30 to 40. You think that's like a reasonable baseline?Swyx [00:36:12]: Right. Right.Philip [00:36:12]: To get to something like 10X, there's a lot of trade-offs that you're making. If we're running at more like a 300, 400 tokens per second range, you are using the best hardware possible. You have a optimized speculator. You have done all of your quantization work. You are Seeing a pretty high cache hit rate. You are running with a reasonably small batch size and a parallelism configuration that is tuned for latency versus throughput, but it is possible. So the spreads that you see if you, like, go on artificial analysis or you go on OpenRouter and you look at, the worst provider to the best provider, oftentimes can hit that range. 10X is of course very aggressive. It's oftentimes maybe more of a four to six times improvement. But that's the performance that makes us really excited, is when we can get these huge gains, not just go from 70 to 90 tokens.Stacking Optimizations: NVFP4, Speculation, and DisaggregationAli [00:37:19]: It's also, like, hardware dependent. Like, ifPhilip [00:37:20]: YeahAli [00:37:20]: If you have a thing where you're serving it on just, like, a node of H100s and then you throw, like, you shard the model across, like, four nodes of B200s. Like, you can definitely increase the speed with just throwing more hardware at it. Like, normalizing for the same exact hardware and the same number of GPUs.Philip [00:37:35]: Yeah. Then you're looking at, like, a two to 4X improvementAli [00:37:38]: Right. RightPhilip [00:37:38]: Depending on the inference optimizations. So yeah, it's. Some of it's, what's the call, and some of it's who's the driver.Vibhu [00:37:46]: If you break down the two to 4X, say the example is run GLM-5.2Ali [00:37:51]: YeahVibhu [00:37:51]: On B200sAli [00:37:53]: YeahVibhu [00:37:53]: Single node, right? What's, like, the cost trade-off for effort to get, like, the last bit of juice out versus what should people just think of, right?Ali [00:38:01]: Spectre quantization. Yeah.Vibhu [00:38:03]: Spectre quantization.Ali [00:38:04]: That's, that's, that's like 95%. LikeVibhu [00:38:06]: And how far does that get you? And how easy is that for the average person to do? So say right I wanna throw the weights of GLM-5.2 on a node of B200s, how easy is it to find speculative decoder- decoder model or already quantized model? How much work goes into it?Philip [00:38:23]: If you're doing it up front, it's quite a lot of work. If you're doing it today, there's going to be people who have published things that you can just, you can just grab some NVFP4 weights. You can grab a speculator. Yeah, if we're thinking about, like, what are the 2Xs we're stacking, going from, BF16 to NVFP4 is, it's not quite a 2X, right? It's like. I think it's about, like, 30 to 40%, from 16 to 8, and then another 30 to 40% multiplied from, 8 to 4. So that doesn't quite get you a 2X, but, like, roughly a 2X. Speculator, roughly a 2X. Disagg on top of that if you're able to get enough hardware and put enough traffic through it, another roughly a 2X. And then you add in some, double-digit percent increase from having just a better runtime with, the latest kernels and stuff behind it. And that's how it stacks up.Ali [00:39:21]: YeahPhilip [00:39:21]: So building each of those, like, building the, quantized weights is, for someone who really knows what they're doing, hours to days of work. Building the speculator, again, like, hours to days of work. And the, disagg setup, hours to days. Well okay, but like once you haveAli [00:39:39]: Once set up. Once set up. YeahPhilip [00:39:40]: Yeah, getting disagg working for the first time, I'm saying, of course, is very difficult.Philip [00:39:44]: The marginal implementationAli [00:39:48]: Like, if you're just grabbing, like if you are a person, like just a normal consumer who has access to, like, a node of B200s and you're wondering, “How can I just host it myself?” You don't need to quantize the model yourself. There's always gonna be, like, an open source quantized checkpoint. NVIDIA's gonna push one out if no one else does. You. Usually, the providers will have their own spec dec that they've trained as well. You don't need to train your own spec dec. You can just use that as well.Philip [00:40:09]: Yeah. Like, GLM-5.2 has its own MTP.Ali [00:40:13]: Right. Right.Vibhu [00:40:14]: What's multi token prediction?Philip [00:40:15]: Yes.Ali [00:40:16]: I'm justVibhu [00:40:16]: Can you explain that?Ali [00:40:16]: I'm just an expert.Ali [00:40:18]: I can do it for you in case I get it wrong?Vibhu [00:40:20]: No.Vibhu [00:40:21]: Yeah, you should correct if we're wrong, but their multi-token prediction can be used for self-speculative decoding.Ali [00:40:27]: I'm not sure. I'm not gonna correct that.Vibhu [00:40:28]: Okay. I'm semi-confident in thatAli [00:40:30]: Okay. YeahVibhu [00:40:30]: But someone can check. But it's useful to paint the story of, okay, not just the average person, but say a company wants to switch from serverless inference I wanna throw this up on. I wanna rent some GPUs, throw it up. These are the steps you take to do significantly faster than just put it behind vLLM.Ali [00:40:48]: Right.Vibhu [00:40:49]: I was waiting for a mention of Dynamo.Vibhu [00:40:51]: I feel like, that's supposed to be the baseline that you measure against.Dynamo, KV Routing, and Disaggregation ToolkitsPhilip [00:40:55]: I would think of Dynamo as less of a box system and more of a toolkit for building with. So when we talk about doing aware routing, when we talk about doing KV offloading, when we talk about doing, PD disaggregation, Dynamo fundamentally is. By the way, Dynamo is an open source library from NVIDIA.Ali [00:41:17]: We've done a pod with KylePhilip [00:41:18]: OkayAli [00:41:19]: Kyle Cranin.Philip [00:41:19]: Cool. So then your listeners know then that it supports all the different inference frameworks. And it is multi hardware, which is interesting.Ali [00:41:28]: But it's just a router, it's not like an optimizer layer.Philip [00:41:30]: Yeah. All it does, like, what Dynamo is good at, it is a library for moving information around your cluster, around your hardware. So if you have, KV cache on one place and you need it to be somewhere else, Dynamo coordinates NIXL for you to move that around.Philip [00:41:49]: That doesn't mean that, like, out of the box, you just say, “Pip install Dynamo,” and then you get, like, a massive performance speed up. It's more of a developer toolkit.Ali [00:42:01]: Yeah. I would have said it would. It comes with a set of defaults that you can then swap out.Philip [00:42:06]: It does. If the industry at large, I think, was, like, rolling out all of these deployments, standard, then I think it would be, like, a credible baseline. But, we've got to, we've got to benchmark against, like, what we're seeing in the wild.Speculative Decoding Methods: Medusa, EAGLE, n-Gram, and Spec-SpecVibhu [00:42:23]: I did wanna talk a little bit more about PD disagg, because that is probably, like, number three after quantized and speculative decoding. In your book though, I was just gonna pull out the book.Philip [00:42:31]: Yeah.Vibhu [00:42:32]: Like section 522 on Medusa, 523 on EAGLEPhilip [00:42:35]: YeahVibhu [00:42:36]: 524 on gram.Philip [00:42:37]: It's 55, would be disaggregationAli [00:42:42]: Yeah. Well, no, I just wanted to dwell a little bitPhilip [00:42:44]: YeahAli [00:42:44]: The other. Like, so what do you choose to include? What do you choose to not to include? Because there was all these other techniques.Philip [00:42:51]: Yeah.Ali [00:42:51]: Are these still relevant? Because I think they came out, like, a year and a half ago maybe.Vibhu [00:42:55]: Medusa is quite old.Philip [00:42:56]: Yeah, Medusa's old.Ali [00:42:58]: It was old.Vibhu [00:42:58]: But is it in the book as a good, here'sPhilip [00:43:01]: BaselineVibhu [00:43:01]: Baseline vanilla understand it?Philip [00:43:02]: Like you should know this.Vibhu [00:43:03]: Like I read the paper, I'm like, “ it makes so much sense.”Philip [00:43:05]: Yeah.Philip [00:43:05]: So with the book, I had a couple goals. One was to give people just a working vocabulary for the space as a whole, and the other was to give them some intuition about how each of these techniques works. As I mentioned in my AI Engineer talk, which is the first public addendum to this, the speculation space has moved much faster than everything else. So yeah, even at the time that I wrote the book Medusa, I very much included as a way for people to understand how the space evolved rather than what the most modern technique is. And now of course, there's DFlash, dSpark. There's, there's newer techniques even than EAGLE, although EAGLE is still very commonly used.Ali [00:43:51]: SpecSpecta.Philip [00:43:52]: Yes. Speculative decoding.Vibhu [00:43:54]: What canAli [00:43:56]: Oh, it's a paper by Tri Dao and it's like, it's doing speculative decodingVibhu [00:44:00]: HuhAli [00:44:01]: For the speculative decoder.Philip [00:44:02]: Oh, in spec- oh my God.Ali [00:44:02]: It's literally just an another. It's like, yeah, that's the most simple way to explain it, and it seems like he got trivial speed ups there. But it seems that the complexity with training, it's almost like in our mind at least, it's almost as complex as training GANs. Like it's like a very delicate balance and oftentimes you, it's just but yeah, it's literally speculative decoding on speculative decoding.Vibhu [00:44:21]: Speculative.Ali [00:44:22]: Yeah. We saw this paper.Vibhu [00:44:24]: It's interesting, right?Ali [00:44:24]: Yeah.Vibhu [00:44:24]: I wouldn't even expect it to be very particular to train, I wouldAli [00:44:29]: Right.Vibhu [00:44:29]: The naive part of me is like, okay, train speculative decoder.Ali [00:44:32]: But like, and it makes sense, like the whole idea of speculative decoding is you. It's like, it's like almost like the iPhone auto predict version but for a normal model, right? Like you're just, you're just, generating three tokens and you're like, okay, I'll do prefill on them. And so you save those three turns for your original model. Now your speculative decoder is doing three turns of auto regression, so why not just have an even smaller model?Ali [00:44:53]: The other question there is what are the size of speculators? So say forPhilip [00:44:58]: Right. It's like a billion parameters.Ali [00:45:01]: Like for MiniMax, it's. Yeah. It's like one layer. It's like one 60th of the original model usually.Philip [00:45:06]: Yeah. I think we should do a paper when we get back to the office.Philip [00:45:10]: SpeculativeAli [00:45:11]: SpeculativePhilip [00:45:11]: Decoding.Ali [00:45:13]: No, it's, it does seem like how, when do you stop? But then it also seems like if you're able to train spec-spec decode for instance, right? Like if you're able to have a small model that is accurately predicts what the intermediate speculator is gonna predict, that is able to predict what the original target model's gonna predict, then why not just use that smallest model directly, right?Vibhu [00:45:34]: Yeah. This isAli [00:45:35]: Like it seems likeVibhu [00:45:35]: Adjacent to the routing problem.Ali [00:45:36]: Right.Vibhu [00:45:36]: Yeah.Ali [00:45:36]: Right.Philip [00:45:37]: The thing with speculators is one of the practical constraints on using them is that you do have to run a small model on the same hardware that you're running the big model on. There is a orchestration and resource competition problem inherent in that, and that is one of the constraints on speculation in general, is that draft tokens cost resources to create and cost software complexity to manage. And so if you have like infinitely recursive speculators, you add in quite a bit of that complexity on the actual implementation within the inference engine as well, not just in the training process.Vibhu [00:46:17]: I was gonna say, I would wonder if you could do similar, like distillation and pruning of, it's the same thing, it's just a model. Can we not just distill a lot of the weights, quantize the speculator, out of my domain? The question that also comes up is, this is all for big server workloads, right? How much of this applies to, say I have this MacBook, I wanna run Gemma really efficiently. Similar problems, not the same?Local AI vs. Data Center InferencePhilip [00:46:45]: Pretty different. I talked to Selo, about this on his podcast a couple weeks ago. The difference between inference engineering for the data center and for production workloads versus inference engineering for local AI, is that we start with fundamentally like different constraints and different goals. With local AI, it's how do I fit this model onto my hardware and then make it less dumb? And with data center influence, it's how do I load this model and then make it less slow? And we care about less dumb, and they care about less slow. But the local AI inference engineering ecosystem, I think has a lot for us to learn from in the data center space. They are experts in various forms of quantization, including dynamic quantization that we just don't touch, in the pruning, in the distillation, in the, layer removal. There'Ali [00:47:42]: Layer removal matters less.Philip [00:47:43]: Yeah. There'Ali [00:47:44]: No one loves pruning really.Philip [00:47:45]: Yeah. Well, but the, but they doVibhu [00:47:46]: Which is surprising, right? But that's, that's a whole different thingPhilip [00:47:48]: Just to fit something on the laptop.Ali [00:47:50]: Right.Philip [00:47:50]: So yeah, it's a, it's an interesting, it's an interesting space. Not necessarily that like their techniques make sense for us to do in the data center, because we have different resources and different goals, but more that the process as well as the openness of that field is something to, admire.Ali [00:48:12]: Yeah. Like to your point, like, certain optimizations that would. Like for instance, Turbo Quantum Sharper, like it made such huge hype on that and we did like a whole deep dive on Twitter and like said, what is it? How does it work? Why is it good or not? And it took off and it was implemented on local devices because your memory bandwidth is so slow on like a MacBook, for instance. But try putting the same thing on like an NVIDIA GPU on a B200 Turbo quant would not be. Like, it would not be used. Like, NVIDIA - Like, NVIDIA made it clear that this is not a good optimization, and we've seen it firsthand where the overhead of doing dequantization, quantization of, in the kernel itself with turbo quant kernel, each end is much slower than the time that you save from doing the bandwidth. ‘Cause on the B200s, you have like 3.5 terabytes per second. You don't need decrease the storage that much. You don't need to do, FP4 KV cache. You don't need to use a requant. There's, there's, there's better optimizations to be made. But on Edge devices, it's extremely important, it's extremely useful. So, seems to be, like, different optimizations there, but then they're all uniquely combined with like all you wanna quantize the model, you wanna do speculative decoding, like certain common prefixes with bothPhilip [00:49:18]: Principles.Ali [00:49:19]: Yeah, exactly. Exactly. Exactly.Philip [00:49:20]: They also do a lot of work on, model parallelism, especially over, heterogeneous topology, where you have, some sparks and they are wired together with, Ethernet, DGX sparks.Ali [00:49:35]: Yeah, this is the Exo Labs guys.Philip [00:49:36]: Yeah. You have, a nu
Episode Title: Paddle Battle: USPA vs UPA Blackout Controversy, Anna Leigh Waters' First Loss & The Future of the Nasty NelsonWelcome back to The Erne with Liam Hoyo! In this episode, we dive into some of the biggest conversations happening in pickleball right now.We break down the ongoing USPA vs UPA paddle certification battle, including what paddle testing means for players, manufacturers, and the future of the sport. We discuss the rise of the “blackout” paddle trend, why paddle approval has become such a hot topic, and how these decisions could impact competitive pickleball.We also analyze Anna Leigh Waters' first loss of the MLP season — what happened, what it means for the best players in the game, and why even the greatest athletes face challenges.Plus, we take a deep dive into one of pickleball's most controversial shots: the Nasty Nelson. We discuss why it creates so much debate, the strategy behind it, the arguments against it, and why it remains one of the most unique parts of pickleball's culture.From paddle technology to pro-level competition and the future of the sport, this episode covers the biggest stories shaping pickleball today.Subscribe to The Erne with Liam Hoyo for more pickleball analysis, coaching insights, player breakdowns, and conversations from around the game.
WWE is steaming toward SummerSlam with AAA and NXT bolstered before multiple shows and lights flashing for AEW All In 2026 -- and Getting Over is here to break it down! Host Adam Silverstein opens with news [3:10] on WWE SummerSlam 2026 and the ESPN deal before tackling three weeks of AAA [16:50], including a huge move for Dominik Mysterio against El Grande Americano and setup for TripleMania 34. "The Silver King" next hits NXT [35:30], where Grayson Waller returned with a pipe bomb, Cruz Montana set the stage for his WWE run and the women showed out, before diving into AEW [58:35] -- featuring Kenny Omega vs. Will Ospreay and Willow Nightingale vs. Mercedes Mone heating up dramatically for All In -- and a month of TNA [1:18:40]. Follow Getting Over on Twitter, Bluesky & YouTube @GettingOverCast.
Joel & Jeremy are not as disgruntled as these guys... Unhappy Grayson Waller's new day in NXT Cruz Montana officially debuts KJ Orso getting a WWE tryout, per Fightful Select Who's coming to MLP? AEW Dynamite Preview & MORE! Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.
Send us Fan MailAnother wild week in Major League Pickleball and lots to cover. This episode covers everything that happened in Chicago, including the biggest controversies on and off the court. Jimmy doesn't hold back with his thoughts on Jim Kloss, we discuss player injuries, MLP professionalism, surprising performances, playoff implications, and preview the massive Orlando finale.00:00 Intro00:53 Disclaimer: Jim Kloss fans beware01:38 Pickler Universe sponsor & MLP Playoffs03:59 Dominator sponsor05:26 KOTC All Access06:56 WNBA highlights & funny discussion08:41 Zane Navratil misses MLP for a wedding12:15 Jim Kloss suite controversy15:54 Jimmy's Jim Kloss rant19:29 Chicago MLP recap begins20:18 Armaan Bhatia injury21:54 Player injuries & contract discussion23:08 Should MLP have injury reports?24:38 Megan Dizon vs. Emma Nelson incident29:23 Chicago Slice surprises everyone32:30 Bears playoff push35:42 Top performers from Chicago37:08 Funny stories from Chicago38:43 Dallas Dominates & JW Johnson40:06 Utah Black Diamonds season recap42:33 Does MLP need a true minor league?48:25 Club Pickleball Mastermind49:53 Rapid-fire questions51:55 Orlando playoff preview57:47 The Kitchen podcast drama59:42 Wrapping upWebsite: https://www.tylerloong.com/ KOTC All Accesshttps://www.youtube.com/channel/UCDiH-sjthLCovD8i79-AkWg/joinCode “KOTC” for insane discounts at: https://www.clubpickleballmastermind.com/kotc KOTC Merch - Use “KOTC” kitchpickleball.comNEW KOTC DISCORD https://discord.com/invite/kNR65mBemfNEW KOTC CAMEOhttps://www.cameo.com/morekotcInstagram: Tyler's IG - @tyler.loong Jimmy's IG - @jimmymiller_pbKOTC IG - @morekingofthecourt Facebook: / tyler.loong --Support the show
Recorded on July/25/2026==========In today's episode of The MBS Show, Norman Sanzo does the show solo and tries not to flub his lines. Join us as we talk and discuss the MLP news of the week and more. It's going to be an awesome episode!!!==========CreditsIntro & Outro Song- Title: The MBS Show Theme Song- Artist: Andy "MandoPony" Stein
Put Your Dusty Cups & Balls in the dishwasher & or tub. On this edition of DGAI we talk about the the possibilities of the recent expiration of 90 day non competes, also the fallout from SNME & the preview of AEW Redemption.Subscribe wherever you get your podcasts and make sure to follow us on socials! All of that and more can be found at http://www.fatalfourpod.comSupport the show and subscribe to the Patreon at http://www.patreon.com/fatalfourpod and for only $3 you'll get Ad Free episodes, bonus content, and access to the exclusive Discord. Or check out Fatal Four Plus! $5/mo gets you access to everything in the $3 tier, plus extra podcasts from the Fatal Four! New ad free bonus shows will drop monthly exclusive to the Fatal Four Plus tier.
This week Laura Royden (@lroyden) makes her second appearance and Allix O (@all_ix) joins the MLP 10-timers club as we have an epic conversation about THE ODYSSEY (in theaters now). We deep dive into the movie, discuss listener feedback, review previous ladder connections and decide on our next connected cinematic rung (2:02:05). Submit your comments, rating and suggested connections for next week's movie to themovieladder@gmail.com.Connect with us on Letterboxd (@TheMovieLadder), Twitter (@LadderMovie) and Instagram (@laddermovie). Check out our Letterboxd watchlist to see all the movies suggested on this podcast. You can find us individually on Twitter (@FitzyBrendan and @brooksza) and Letterboxd (@FitzyBrendan and @brooksza). And join us for the Ladder Library Movie Challenge in 2026.
Send us Fan MailThe MLP season just got even more interesting.In this episode of King of the Court, Tyler Loong and Jimmy Miller break down everything that happened at MLP San Diego, discuss the latest trade rumors around the league, analyze the Dallas Flash's surprising championship run, and preview the upcoming Chicago event.0:00 Intro0:11 Tyler's brutal drive home from San Diego3:18 Meeting King of the Court fans5:28 Pickler Universe sponsor8:39 MLP playoff race update9:14 Dominator sponsor11:00 KOTC All Access11:53 World Cup & soccer discussion12:49 Mile world record broken14:08 Caitlin Clark's historic performance14:42 MLP trade deadline rumors15:53 Federico Staksrud's illness in San Diego16:48 Why roster depth matters in MLP22:50 Black Bears recap vs. Phoenix24:22 Dallas Flash's shocking championship run26:45 LA Mad Drops struggle in San Diego28:17 Connor Garnett traded to LA30:14 Why LA moved on from Gabe Joseph30:56 Should LA have signed Colin Johns?33:18 San Diego venue review35:46 Club Pickleball Mastermind sponsor37:51 San Diego fan atmosphere39:19 Should MLP limit player trades?41:21 The human side of player trades44:54 Chicago MLP preview46:28 Teams fighting for playoff spots50:56 Questions from listeners53:47 Tyler explains his trade experience56:02 Irina Tereschenko's incredible emergency sub performance57:43 California Black Bears explained58:23 Targeting weaker players in MLP strategy1:00:36 QuestionsWebsite: https://www.tylerloong.com/ KOTC All Accesshttps://www.youtube.com/channel/UCDiH-sjthLCovD8i79-AkWg/joinCode “KOTC” for insane discounts at: https://www.clubpickleballmastermind.com/kotcKOTC Merch - Use “KOTC” kitchpickleball.comNEW KOTC DISCORD https://discord.com/invite/kNR65mBemfNEW KOTC CAMEOhttps://www.cameo.com/morekotcInstagram: Tyler's IG - @tyler.loong Jimmy's IG - @jimmymiller_pbKOTC IG - @morekingofthecourt Facebook: / tyler.loong --Support the show
El Wrestling Canadiense vuelve por fin a la televisión, y ARDL no podía faltar en este momento tan importante. Andrés Bahamonde (@ElQueYaNoBebe) y Paulina Cárcamo (@NueveReinass) comentan todo lo sucedido en la Season Premiere de MLP Mayhem. Stu Grayson se enfrenta a Jonathan Gresham por el campeonato interino Canadiense de MLP, la aparición de la joven promesa Rhino, los Grizzle Young Veterans dando una muy buena impresión, Johnny TV amenaza con robarse el protagonismo, Gisele Shaw defiende el campeonato femenino Canadiense de MLP, y mucho más.
5 SETTER: This Week in Racket Sports, where we bring you the top five headlines across tennis, padel, pickleball, and more. Wimbledon 2026 is in the books — Jannik Sinner claimed his fifth Grand Slam title, Serena Williams drew the biggest Wimbledon audience in ESPN history, and the women's final set an all-time record. Plus, Carlos Alcaraz has been cleared to return, and the tennis world cleaned up at the altar. Check out Andy's Wilson Defyer Review: https://youtu.be/nMXWrYafeAI In this episode, we cover the biggest stories shaking up the world of racket sports: 1. Wimbledon 2026 viewership records 2. 2026 Cincinnati Open entry list 3. Novak Djokovic "The Wolf in Winter" documentary trailer drops on Prime Video 4. Tennis wedding roundup 5. Anna Leigh Waters' MLP women's doubles win streak snapped at 25-0 If you follow pro tennis, play padel or pickleball, or just want to stay in the loop with the fastest-growing sports on the planet, this is your weekly fix. Subscribe for weekly episodes covering major stories, sharp insights, and fun surprises in the world of racket sports. COMMENT BELOW What was your favorite racket story from this week?
Ravenous Rohan Raja is a British-Indian professional wrestler known for his hard-hitting style, technical ability, and commanding presence in the ring. Best known for his time in NXT UK and now making an impact in Maple Leaf Pro Wrestling, Raja has built a reputation as one of the UK's top talents while continuing to establish himself on the international wrestling scene.In the newest "Casual Conversations with The Classic'' episode, the Wrestling Classic Justin chats Ravenous Rohan Raja as they discuss Maple Leaf Pro Wrestling. breaking into wrestling as an Indian, representation, WWE UK, Storm Academy and more! Enjoy!We appreciate you visiting our YouTube Channel! Please subscribe, like and engage!My Official Website + Demo Reel - https://www.justindhillon.com Instagram - https://www.instagram.com/thewrestlingclassic/ TikTok - https://www.tiktok.com/@thewrestlingclassic X - https://x.com/twcworldwide Youtube - https://www.youtube.com/@TheWrestlingClassic/ Limited Edition TWC Tee https://headquartersclothing.com/products/headquarters-x-the-wrestling-classic-logo-tee?_pos=1&_psq=wrestlinhg&_ss=e&_v=1.0 WWE Shop Affiliate wwe-shop.sjv.io/RGRxQv 500 Level https://www.500level.com/ Join the Discord Community https://linktr.ee/thewrestlingclassic All Episodes are on "The Wrestling Classic" Youtube Channel https://www.youtube.com/channel/UCOQOYraeFlX-xd8f3adQtTw#RohanRaja #Ravenous #MLPWrestling #MapleLeafProWrestlingBecome a supporter of this podcast: https://www.spreaker.com/podcast/twc-show--4417554/support.
Send us Fan MailThe King of the Court Podcast is back!This week Tyler Loong and Jimmy Miller break down everything that happened at the Beer City Open (BCO), discuss the future of Major League Pickleball, and explain why a salary cap could completely reshape the league.0:00 Should pro players be allowed to gamble?0:47 Welcome back & crazy stories from BCO1:44 Beer City Open recap2:39 World Cup discussion5:09 McGregor vs Holloway reaction6:33 Pickler Universe playoff announcement10:43 Dominator sponsor12:20 KOTC All Access13:50 Fan feedback from last week's episode15:39 Players missing BCO19:27 International & College teams at BCO20:54 One Point Challenge discussion21:37 BCO tournament recap26:29 Shock vs Mad Drops breakdown29:30 The Miami Pickleball Club "Fives" jerseys30:09 Annalie Waters strategy debate36:20 MLP salary cap explained41:37 Club Pickleball Mastermind43:12 San Diego MLP preview50:11 The business side of player trades56:00 Listener Q&A56:42 Is MLP becoming boring?57:28 Tyler vs Tama singles?59:01 Trade deadline changes1:01:14 Behind the scenes with the MLP MC1:01:45 Dallas vs Newport playoff format explained1:03:33 The Dink premiere1:04:21 Final thoughts & outroWebsite: https://www.tylerloong.com/ KOTC All Accesshttps://www.youtube.com/channel/UCDiH-sjthLCovD8i79-AkWg/joinCode “KOTC” for insane discounts at: https://www.clubpickleballmastermind.com/kotc Use Code "KOTC" for Big Savings on Vulcan Gear: https://vulcansportinggoods.com/pagesKOTC Merch - Use “KOTC” kitchpickleball.comNEW KOTC DISCORD https://discord.com/invite/kNR65mBemfNEW KOTC CAMEOhttps://www.cameo.com/morekotcInstagram: Tyler's IG - @tyler.loong Jimmy's IG - @jimmymiller_pbKOTC IG - @morekingofthecourt Facebook: / tyler.loong --Support the show
00:00:00 NEWSEl Generico loses the big oneTony Khan brings back the territories (MLP on MyAEW)Flatpak ConclusionPenultimate World Cup Update10k00:26:28 QsFantasy UpdateOney Lorcannect00:49:10 REVIEWSDynamiteCollisionG1 Night 1Dark Side of the Ring - Jeff Jarrett and the Battle for TNA (Part 1 & 2)02:05:08 MOVIESBlue HeronThe FuriousCarolina Caroline02:19:51 TV25 Years of The Office
Zane is fresh off a trip to PPA Tokyo and lands straight in Grand Rapids for the Beer City Open / MLP Mid-Season Tournament — so he and Nico have a lot to cover. They break down the mysterious dueling "Team USA" pickleball announcements, preview Match Day prop bets for the Beer City Open, draft the most Silent Assassins in an MLP-style event, and dig into Jay Devilliers' surprise move to the APP Tour ahead of a wave of expiring PPA contracts. Plus: Zane's Tokyo recap (sumo wrestling included), MLP trade deadline predictions, and a new Guess My Duper.
Send us Fan MailThe MLP Mid-Season Tournament is finally here, and we're breaking down everything you need to know before the action begins in Grand Rapids.This week we preview every first-round matchup, discuss which teams have the best chance to make a run, and debate whether Australia or any of the international teams can pull off an upset.We also dive into one of the biggest conversations in Major League Pickleball this season: strength of schedule, championship court exposure, and whether every team is truly getting a fair opportunity.00:00 Happy 4th of July & Utah fireworks discussion03:11 Pickler Universe spotlight & Austrian Open success05:23 Dominator sponsor spotlight07:30 KOTC All Access update08:08 World Cup talk & Mexico vs England09:42 BCO Mid-Season Tournament preview begins10:32 Breaking down the international teams13:18 First-round matchup predictions15:05 Will players opt out of BCO?18:19 Explaining the double-elimination format20:38 FOX & FS1 broadcast schedule21:37 Championship predictions22:24 Outdoor conditions & Grand Rapids weather25:28 MLP strength of schedule controversy31:22 Championship Court fairness debate36:40 Should pickleball referees wear cameras?38:52 What does pickleball need to become mainstream?41:43 Why Grand Slams matter for pickleball's future46:16 Tyler responds to online criticism57:44 Club Pickleball Mastermind1:00:09 Reacting to "Pickleball Is Dying"1:03:50 Brand loyalty & constant player movement in MLP1:06:38 Bobby Bonilla Day & deferred contracts in sports1:09:00+ More MLP business discussion & player contracts (continues)Website: https://www.tylerloong.com/ KOTC All Accesshttps://www.youtube.com/channel/UCDiH-sjthLCovD8i79-AkWg/joinCode “KOTC” for insane discounts at: https://www.clubpickleballmastermind.com/kotc Use Code "KOTC" for Big Savings on Vulcan Gear: https://vulcansportinggoods.com/pagesKOTC Merch - Use “KOTC” kitchpickleball.comNEW KOTC DISCORD https://discord.com/invite/kNR65mBemfNEW KOTC CAMEOhttps://www.cameo.com/morekotcInstagram: Tyler's IG - @tyler.loong Jimmy's IG - @jimmymiller_pbKOTC IG - @morekingofthecourt Facebook: / tyler.loong --Support the show
Zane's calling in from a hostel kitchen in Tokyo and Nico's posted up at Gino the Righty's place in California, but somehow they still pulled off the wildest PicklePod yet. This week: the New Jersey Fives win their third straight MLP event and take over first place in the standings, the league's first-ever four-team trade reshuffles the Chicago Slice and St. Louis Shock, and the guys break down the Casey Diamond/Grayson Goldin injured reserve controversy that's got every GM in the league fired up. Oh, and we finally talk about the scoreboard that collapsed on Brooklyn's Rachel Rohrabacher mid-match — and why MLP's statement on it might have made things worse.
Send us Fan MailThe professional pickleball world had one of its craziest weeks yet.Tyler Loong and Jimmy Miller break down everything from the shocking Rachel R scoreboard incident, controversial MLP trades, surprising upsets, DreamBreakers, player hype, league issues, and what needs to change if professional pickleball wants to continue growing.00:00 Fan behavior & where the line is00:48 Welcome back01:35 World Cup discussion04:18 Club Pickleball Mastermind05:00 Pickler Universe07:36 Dominator08:23 KOTC All Access09:10 MLP New York recap09:57 Massive MLP trade explained12:24 Hunter Johnson, Elsie & JLG trade14:02 Why third players matter more than ever14:44 Ross Chaffetz's farewell post17:45 Did Chicago make the right move?18:33 Is Elsie Hendershot overhyped?24:48 Stop comparing players to Annalee Waters27:16 Carolina shocks Palm Beach29:36 Players leaving MLP events32:12 Does MLP need stricter rules?34:28 Rachel Rohrabacher scoreboard incident37:46 Should players receive compensation?39:36 Bobby's Guy Fieri outfit40:21 PPA's official response40:58 Court spacing problems41:45 DreamBreaker recap44:10 Ranchers upset the Five's44:59 MLP standings update49:03 Should the Mad Drops trade Max Freeman?52:52 Third players becoming more valuable53:36 Florida Smash drops Travis Rettenmaier58:02 Professional commentary discussion1:01:29 Jared Paul & The Kitchen discussion1:08:05 Which players deserve the hype?Website: https://www.tylerloong.com/ KOTC All Accesshttps://www.youtube.com/channel/UCDiH-sjthLCovD8i79-AkWg/joinCode “KOTC” for insane discounts at: https://www.clubpickleballmastermind.com/kotc Use Code "KOTC" for Big Savings on Vulcan Gear: https://vulcansportinggoods.com/pagesKOTC Merch - Use “KOTC” kitchpickleball.comNEW KOTC DISCORD https://discord.com/invite/kNR65mBemfNEW KOTC CAMEOhttps://www.cameo.com/morekotcInstagram: Tyler's IG - @tyler.loong Jimmy's IG - @jimmymiller_pbKOTC IG - @morekingofthecourt Facebook: / tyler.loong --Support the show
This might be the biggest news week in MLP history. Zane and Nico break down the Hurricane Tyra Black ↔ Danni-Elle Townsend trade, debate whether the New Jersey 5s need to make a move of their own, and dig into salary floor/cap rumors that could reshape the league. Then Danni-Elle Townsend joins fresh off the trade to tell her side of the story, followed by Florida Smash's Zoey Weil for a no-holds-barred conversation on the Jay Devilliers/Lea Jansen blowup, the "body bag" debate, and her ongoing beef with Jim Closs.
Send us Fan MailMLP Austin delivered one of the wildest weekends of the season.In this episode of KOTC, Tyler and Jimmy break down the biggest storylines from Austin, including player absences, controversial no-shows, heated on-court drama, major trade news, and a full recap of Championship Sunday.The guys discuss the Dallas Flash's shocking performance, the blockbuster Tyra Black trade, Jay D latest controversy involving Lea Jansen and Nico Acevedo, and whether MLP teams are entering buyer-or-seller mode ahead of the trade deadline.0:00 Super Sunday belt discussion0:48 Welcome back to King of the Court1:08 Club Pickleball Mastermind sponsor spotlight3:08 Club Pickleball Sandy location review3:49 Pickler Universe update and ticket information5:32 Indoor vs outdoor pro pickleball debate6:14 Dominator sponsorship spotlight6:58 KOTC All Access update7:38 "You're taller than Tyler" fan interaction8:15 Listener bike crash story9:33 NBA Finals and New York Knicks discussion11:49 Museum of Ice Cream video update12:31 MLP Austin recap begins13:24 Player absences and no-show controversy15:03 Load management discussion in MLP16:32 Why showing up matters for your team17:16 Jesse Irvin's impressive performance while sick19:34 Tyler reflects on competing with a broken hand20:15 Team accountability and leadership21:26 Do star players face consequences?22:05 J-Dub vs Nico Acevedo incident23:45 Lea Jansen responds to J-Dub25:13 Was the controversy overblown?27:27 Florida Smash shocks Dallas Flash29:08 Len Yang and Pablo Tellez impress29:48 Utah Black Diamonds vs Columbus Sliders30:44 James Delgado shines in mixed doubles31:29 Texas Ranchers dominate Dallas Flash32:11 Austin fan attendance review32:51 Every match mattered in Austin34:25 Trae Young attends MLP Austin35:16 Dallas Flash vs Miami Pickleball Club thriller36:56 Emma Nelson continues to impress38:21 Why young players are taking over pickleball39:50 Championship Sunday recap40:42 Tyra Black traded to Columbus42:30 Why Columbus made the move43:18 What Dallas gains from the trade44:02 Potential future trade scenarios45:32 Other trade deadline candidates46:16 MLP roster construction rules explained46:58 Jimmy apologizes to Dekel Bar48:40 St. Petersburg MLP preview49:31 Pool changes explained50:18 Growth of MLP and Austin success51:08 Austin venue and court conditions review53:15 St. Pete Athletic Club preview54:03 Early St. Pete matchups55:28 Group A predictions58:20 Group B predictions59:53 Travis Rettenmaier injury update1:00:44 How did Dallas finish last?1:01:41 Was trading Tyra the right move?1:02:35 Should players be traded mid-season?1:04:10 Is the MLP trade deadline too long?1:04:58 Why isn't Rafa Hewett on an MLP roster?1:05:52 Ideal pro pickleball facility discussion1:06:43 Does Dallas need additional support?1:07:32 Annalee Waters and Anna Bright discussion1:09:10 How to join the KOTC Discord1:09:49 ATP strategy discussion1:10:32 Final thoughts and St. Pete excitementWebsite: https://www.tylerloong.com/ KOTC All Accesshttps://www.youtube.com/channel/UCDiH-sjthLCovD8i79-AkWg/joinCode “KOTC” for insane discounts at: https://www.clubpickleballmastermind.com/kotc Use Code "KOTC" for Big Savings on Vulcan Gear: https://vulcansportinggoods.com/pagesKOTC Merch - Use “KOTC” kitchpickleball.comNEW KOTC DISCORD https://discord.com/invite/kNR65mBemfNEW KOTC CAMEOhttps://www.cameo.com/morekotcInstagram: Tyler's IG - @tyler.loong Jimmy's IG - @jimmymiller_pbKOTC IG - @morekingofthecourt Facebook: / tyler.loong --Support the show
Send us Fan MailKOTC breaks down everything that happened at MLP St. Louis, including the controversial court conditions, Riley Newman's injury, DreamBreaker strategy debates, and which teams are rising or falling after another major league event.We discuss:The rollout court controversy in St. Louis Why players were frustrated with the venue setup Riley Newman's injury and Brooklyn's outlook Phoenix vs Vegas DreamBreaker strategy breakdown Which players are trending up and down MLP trade rumors and potential roster moves Austin MLP preview and predictions Crypto, SpaceX and fan Q&APlus, Jimmy and Tyler give their honest thoughts on the current state of Major League Pickleball and what teams should do before the trade deadline.Timestamps00:00 Intro & Off Campus Discussion00:52 Welcome Back to KOTC01:16 Club Pickleball Mastermind03:00 Pickler Universe Update05:02 Dominator Sponsor Segment07:23 MLP St. Louis Overview08:14 Court Surface & Bounce Issues09:43 Arena Experience vs Facility Problems13:22 Indoor Arena Debate14:00 Fan Encounters & Cindy Kaoimoto16:14 Riley Newman Injury Update17:41 St. Louis Shock Dominance19:41 Million Dollar AB Discussion21:21 Phoenix vs Vegas DreamBreaker Breakdown28:39 What's Wrong with the Bouncers?29:28 St. Louis Group Results Recap30:57 MLP Scheduling Problems36:47 Trade Rumors Begin39:17 Dylan Frazier & Nico Acevedo Discussion40:56 Connor Garnett Trade Possibilities43:07 Building for the Future vs Winning Now44:34 MLP Parity Discussion45:51 Indoor Facility Potential46:37 Austin MLP Preview48:56 Austin Weather & Event Concerns50:28 KOTC All Access Update51:57 Austin Pool Breakdown58:05 Ranchers & Nico Acevedo Outlook01:00:54 Austin Predictions01:02:16 Fan Q&A Begins01:02:30 Biggest Risers in MLP01:04:01 Biggest Disappointments So Far01:06:45 Will MLP Change Player Contracts?01:07:34 Shock Merchandise Discussion01:07:34 James Delgado & Pickleball IQ01:08:18 Is Brooklyn Underrated?01:09:09 Bitcoin, Pengu & SpaceX01:10:41 If Hayden & Gabe Teamed Up...Website: https://www.tylerloong.com/ KOTC All Accesshttps://www.youtube.com/channel/UCDiH-sjthLCovD8i79-AkWg/joinCode “KOTC” for insane discounts at: https://www.clubpickleballmastermind.com/kotc Use Code "KOTC" for Big Savings on Vulcan Gear: https://vulcansportinggoods.com/pagesKOTC Merch - Use “KOTC” kitchpickleball.comNEW KOTC DISCORD https://discord.com/invite/kNR65mBemfNEW KOTC CAMEOhttps://www.cameo.com/morekotcInstagram: Tyler's IG - @tyler.loong Jimmy's IG - @jimmymiller_pbKOTC IG - @morekingofthecourt Facebook: / tyler.loong --Support the show
Last week Zane called out Hayden Patriquin's Columbus performance. Hayden texted back one sentence — and then went 10-0 in St. Louis. We cover all of that, the Shock's total demolition of the Mad Drops, a deep dive on how to actually beat Ben Johns, and full MLP power rankings with a new segment: the James Ignatowich Terminated Team of the Week.
Zane's calling in from Match Point Pickleball in Columbus (winners of the Dink Award for best pickleball facility) after surviving a six-hour clinic, MLP, and accidentally yelling "Let's go 5s" for his old team. Classic. We break down everything from MLP Columbus — New Jersey Fives sweep their way to 25 standings points, St. Louis Shock falters, and Zane comes THIS close to beating Anna Leigh Waters in mixed doubles. Plus: Grayson Goldin's jaw-dropping Dreambreaker win just months after suffering two strokes, the Genie Bouchard situation explained, Anna Bright goes viral on X, and the moment you've been waiting for — the MLP Vibes-Only Draft. Subscribe and let us know: Who has the highest ceiling in pickleball right now?
Send us Fan MailWelcome back to another episode of KOTC! This week Tyler Loong & Jimmy Miller break down everything from MLP Columbus, including the California Black Bears' performance, the continued struggles of the St. Louis Shock despite one of the most expensive rosters in MLP history, and whether the pickleball world is too quick to overreact to a single event.The guys discuss the recent Genie Bouchard trade, Alix Truong's move to the Flames, the Palm Beach Royals' roster decisions, and why one-game-to-11 MLP matches can create some wild results. They also dive into the ongoing debate surrounding international PPA points, John McEnroe's comments about pickleball, and whether top pros should be stronger ambassadors for the sport.Plus: MLP St. Louis preview, Anna Bright and the pressure facing the Shock, championship ceremony controversy, and Tyler's now-infamous Museum of Ice Cream golden spoon story.Timestamps0:00 Intro & Shock Super Sunday jokes 1:35 Club Pickleball Mastermind sponsor 3:01 Pickler Universe update 5:00 Dominator sponsor 7:02 KOTC discount code update 8:37 KOTC All Access membership 9:20 Tyler's New York story begins 10:01 Museum of Ice Cream & the golden spoon controversy 13:54 Pickleball destroying a marriage? 16:45 MLP Columbus recap begins 17:39 Jeannie Bouchard traded to Carolina 18:10 California Black Bears weekend recap 19:35 Miami Hogs stock discussion 20:26 Are people overreacting to MLP results? 22:08 St. Louis Shock concerns 22:50 Why haven't the Shock won yet? 24:58 Should the Shock make a blockbuster trade? 27:06 MLP St. Louis preview 28:50 Breaking down the St. Louis groups 29:53 Rumored Shock player contracts 31:32 Pressure building for St. Louis 32:21 Brooklyn and Utah outlook 33:06 Is Jaume Martinez Vich better on the left? 33:53 Paris Todd controversy & comments 35:26 Relatability of pro pickleball stars 36:59 International PPA points discussion 39:04 Do international points need adjustment? 41:19 LeBron's dark mode strategy 42:14 Should Anna Bright go dark mode? 43:44 Columbus venue, courts & lighting review 44:26 Championship ceremony controversy 47:20 Alex Strong trade analysis 48:56 Columbus team chemistry concerns 49:48 Palm Beach Royals discussion 53:00 John McEnroe, Jeannie Bouchard & pickleball criticism 57:29 What should ambassadors of the sport do? 58:59 Final thoughts on St. Louis 59:45 Why MLP is different than PPA events 1:01:58 OutroWebsite: https://www.tylerloong.com/ KOTC All Accesshttps://www.youtube.com/channel/UCDiH-sjthLCovD8i79-AkWg/joinCode “KOTC” for insane discounts at: https://www.clubpickleballmastermind.com/kotc Use Code "KOTC" for Big Savings on Vulcan Gear: https://vulcansportinggoods.com/pagesKOTC Merch - Use “KOTC” kitchpickleball.comNEW KOTC DISCORD https://discord.com/invite/kNR65mBemfNEW KOTC CAMEOhttps://www.cameo.com/morekotcInstagram: Tyler's IG - @tyler.loong Jimmy's IG - @jimmymiller_pbKOTC IG - @morekingofthecourt Facebook: / tyler.loong --Support the show
Executive producer Mark Infante and pro pickleball star Anna Bright join Kate to talk about PARTNERS, the six-part Prime Video documentary series following the meteoric rise of the Professional Pickleball Association (PPA), the league that, in less than five years, has gone from scrappy upstart to the center of an international phenomenon. Anna Bright is a former Division I tennis standout at UC Berkeley turned top-ranked PPA and MLP pro, known for her aggressive style, lethal two-handed backhand, and high-profile partnership with world No. 1 Anna Leigh Waters. She gives a rare inside look at life on tour: how the sport actually works, what sets it apart, the wild financial transformation of pro pickleball, and the rivalries and romances that make the league must-watch TV. Reality Life with Kate Casey What to Watch List: https://katecasey.substack.com The Story Behind My Podcast: https://katecasey.substack.com/p/i-was-the-narrator-of-my-own-family Patreon: http://www.patreon.com/katecasey Twitter: https://twitter.com/katecasey Instagram: http://www.instagram.com/katecaseyca Tik Tok: https://www.tiktok.com/@itskatecasey?lang=en Facebook Group: https://www.facebook.com/groups/113157919338245 Amazon List: https://www.amazon.com/shop/katecasey Like it to Know It: https://www.shopltk.com/explore/katecaseySee Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
MLP is BACK — and Week 1 in Dallas did not disappoint. The Mad Drops took the whole thing, Ben Johns reminded everyone he is NOT to be slept on, and Danny Townsend made the entire pickleball world do a double-take. Nico and Zane break it all down. Also this week: The Philippines tournament chaos (double gold, two balls, no final), Bao Duong absolutely owns Nico in a text exchange, Owl AI line-calling under the microscope, and Guess My Duper is back. Subscribe and let us know: Who has the highest ceiling in pickleball right now?
Send us Fan MailKOTC is back breaking down EVERYTHING from the wild MLP Dallas weekend at Pickler Universe — including the controversial new MLP rules, Ben Johns' dominant performance, DreamBreaker strategy, player rankings drama, and whether international PPA events are gaming the system.Tyler and Jimmy discuss the chaos surrounding blue cards, standing restrictions, phone bans, injury replacements, singles specialists, and the biggest winners and losers from the event. They also dive into Utah Black Diamonds, Dallas Flash struggles, Mad Drops' championship run, and what to expect heading into Columbus.Make sure to LIKE, SUBSCRIBE, and join the KOTC All-Access membership for bonus content, gossip, breaking news, and behind-the-scenes discussions.Timestamps 00:00 Intro + AI line call rant00:52 Youth sports & “plastic rings” discussion02:15 Dallas trip recap + Chili's review03:53 Club Pickleball Mastermind sponsor11:48 PPA Asia ranking controversy begins20:34 MLP Dallas recap begins21:50 New MLP rules explained22:35 Fed's blue card comments24:01 Why the new bench rule hurts MLP25:36 Cell phone bans & gambling concerns26:13 Blue card controversy with Bay Area26:55 Utah challenge timeout mistake explained28:17 MLP energy & atmosphere discussion29:02 Injury replacements & alternates chaos31:52 Singles specialists discussion33:22 DreamBreaker importance this season34:45 Communication issues with singles specialists41:09 Biggest losers from MLP Dallas43:48 Utah Black Diamonds analysis45:59 Connor Garnett & Tama breakdown47:35 Pablo Tellez praise + Utah struggles48:31 Surprise performances from the weekend49:17 Best player at MLP Dallas50:07 Young teams analysis (Phoenix & Bay Area)51:36 Luka Mack injury + Joey Wild signing52:31 Columbus MLP preview53:10 Georgia Johnson/JW matchup controversy54:39 Pickler Universe crowd & atmosphere55:32 Columbus team pools breakdown57:00 New MLP format discussion57:47 Columbus preview continues58:33 KOTC All-Access membership plug59:25 Columbus women's lineup debate01:00:14 Questions01:10:28 Final thoughts & outroWebsite: https://www.tylerloong.com/ KOTC All Accesshttps://www.youtube.com/channel/UCDiH-sjthLCovD8i79-AkWg/joinCode “KOTC” for insane discounts at: https://www.clubpickleballmastermind.com/kotc Use Code "KOTC" for Big Savings on Vulcan Gear: https://vulcansportinggoods.com/pagesKOTC Merch - Use “KOTC” kitchpickleball.comNEW KOTC DISCORD https://discord.com/invite/kNR65mBemfNEW KOTC CAMEOhttps://www.cameo.com/morekotcInstagram: Tyler's IG - @tyler.loong Jimmy's IG - @jimmymiller_pbKOTC IG - @morekingofthecourt Facebook: / tyler.loong --Support the show
Major League Pickleball is back, and Commissioner Samin Odhwani joined PicklePod to explain all of the new changes heading into the season. We break down: - The new MLP tournament format - Super Sunday / Super Monday explained - Dreambreaker substitution strategy - MLP Asia plans - Why million-dollar player spending may not be sustainable - The biggest challenge facing MLP's future Samin also discusses where MLP is headed long term and what still needs to be fixed. Subscribe for more PicklePod episodes, pro interviews, and pickleball news. #pickleball #mlp #majorleaguepickleball #picklepod Be the first to try Zane's new course here: https://tzpickleball.com/ Check out Zane's Pro Pickleball Talk channel on Discord: https://discord.gg/wzNVADmZb #Pickleball #PPATour #PickleballPodcast Leave your voicemail for the PicklePod at (512) 200 - 4299 ------------------ Like the ep? Do us a favor: subscribe to our channel and leave a review on Apple or Spotify -Subscribe to our 'all things pickleball' *free e-newsletter* at https://www.thedink.beehiiv.com https://www.instagram.com/thedinkpickleball/ -Follow us on IG -Continue the convo in our private FB Group: https://www.facebook.com/groups/thedi... -For everything else we do, visit https://linktr.ee/dinkfam -Read more about Zane and subscribe to his newsletter at https://zanenavratilpickleball.com/ -Follow Zane on IG @zanenavratilpickleball #pickleball #pickleballcourts ------------------ Learn more about your ad choices. Visit megaphone.fm/adchoices
For this week's PicklePod, we're joined by two of the most exciting young stars in pickleball: Hayden Patriquin and Gabe Tardio of the St. Louis Shock. We dive into everything from Shock team culture and MLP pressure to why Gabe ignored traditional pickleball advice and built his own game from scratch. Hayden also opens up about his on-court personality, social media backlash, and finding the balance between playing with emotion and staying under control. We also get into: - The “Shock are chokers” debate - Why Hayden might have the highest ceiling in pickleball - What makes Ben Johns so difficult to beat - Signature shots and unique techniques - The future of pickleball strategy - Gambling stories, trash talk, and complete chaos This episode goes all over the place in the best way possible. One minute we're breaking down elite strategy and the next we're talking baccarat, sleep habits, and why nobody actually knows the “right” way to play pickleball. Subscribe and let us know: Who has the highest ceiling in pickleball right now?
Send us Fan MailIn this episode of King of the Court, Tyler and Jimmy break down everything heading into the first Major League Pickleball event of the season at Pickler Universe in Dallas. They preview the biggest matchups, debate new team lineups, discuss waiver wire moves, and analyze how teams might use younger players this season.Jimmy/Tyler also recap PPA Asia, react to rumors surrounding new partnerships, discuss the economics behind MLP and why fans can't expect “backyard pickleball” access forever, and a local Utah moneyball meltdown.Plus: JW Johnson & Tama rumors, Ben Johns, the New Jersey 5s, MLP team loyalty, Lifetime balls, podcast consistency, fake Discords, and much more.Timestamps00:00 intro 06:40 Club Pickleball Mastermind 08:03 Pickler Universe giveaway recap 13:56 PPA Asia recap begins 16:44 Women's singles results 17:03 Men's singles recap + Zane Navratil loss 18:04 Mixed doubles results 18:52 Women's doubles recap 19:43 Colin Johns wins gold in men's doubles 22:59 Should Asia events count for full points? 24:37 Jimmy's MLP rant begins 29:12 Ryan Smith & Utah sports culture comparison 29:53 Teams treating players differently 32:39 MLP loyalty discussion 33:22 Players being dropped without warning 42:32 Orlando Squeeze vs Dallas Flash 43:28 Flash vs New Jersey 5s hype matchup 46:51 Shock vs Mad Drops marquee matchup 48:21 Teams with lineup flexibility 49:03 Should teams develop younger players? 52:41 Bay Area Bears strategy discussion 53:26 Vegas Night Owls lineup rumors 56:18 Why MLP strategy will be fascinating 56:59 No more bench switching 57:51 Indoor MLP events this season 58:35 Lifetime pickleballs discussion 59:19 Vulcan V-Pro Flight sponsor segment 01:01:00 questions begin 01:01:50 PPA Challengers vs APP winners 01:02:35 Canadian PPA events discussion 01:03:23 Tyler vs Tyson McGuffin hypothetical 01:04:14 Why podcasts fail 01:05:01 KOTC 3-year anniversary discussion 01:05:50 Free merch discussion 01:06:37 Fake Discord warnings 01:07:33 Favorite music discussion 01:08:21 JW Johnson & Tama partnership rumor 01:09:09 Should JW move to the right side?Website: https://www.tylerloong.com/ KOTC All Accesshttps://www.youtube.com/channel/UCDiH-sjthLCovD8i79-AkWg/joinCode “KOTC” for insane discounts at: https://www.clubpickleballmastermind.com/kotc Use Code "KOTC" for Big Savings on Vulcan Gear: https://vulcansportinggoods.com/pagesKOTC Merch - Use “KOTC” kitchpickleball.comNEW KOTC DISCORD https://discord.com/invite/kNR65mBemfNEW KOTC CAMEOhttps://www.cameo.com/morekotcInstagram: Tyler's IG - @tyler.loong Jimmy's IG - @jimmymiller_pbKOTC IG - @morekingofthecourt Facebook: / tyler.loong --Support the show
Send us Fan MailIn this episode of King of the Court, Tyler and Jimmy break down everything from the PPA Finals and San Clemente 500, including partnership rumors, controversial line-calling technology, MLP storylines, and the future of pro pickleball. Jimmy absolutely unloads on the New Jersey 5s logo, while Tyler shares behind-the-scenes stories from competing in the finals himself.We also discuss Ben Johns and ALW continuing their dominance, Kate Fahey's big win, possible men's doubles shakeups, Nico Acevedo's rise, the “Partners” documentary, sponsorship money in pickleball, and why some players may already be searching for new partners. Plus, we talk Pickler Universe, upcoming MLP events, court surface issues, and some wild behind-the-scenes stories from San Clemente.If you enjoy honest conversations, pickleball drama, player insight, and all the latest pro pickleball news, make sure to subscribe and join the KOTC community.00:00 – Intro 00:49 – Jimmy Rips the New Jersey 5s Logo04:06 – Sponsors07:03 – Pickler Universe Giveaway Call11:54 – Why Pickler Universe Is the Best MLP Venue18:37 – San Clemente Parking & Venue Stories19:18 – Court Surface Problems & Dead Spots22:05 – New Line Calling Technology Discussion24:07 – How Accurate Is the AI Line Call System?27:42 – PPA Finals Points System Explained31:39 – Why the Rich Get Richer in Rankings32:24 – Men's Singles Recap (JLG, Garnett & More)34:00 – Players Pulling Out of Events34:40 – “Partners” Documentary Reactions39:10 – Kevin Hart Roast Reactions41:35 – Mixed Doubles Recap42:33 – Ben Johns vs ALW Debate44:50 – Should PPA Randomize Mixed Partners?47:05 – Tyler's Finals Match & Mid-Match Rule Change51:25 – Alshon's Viral Interview Reactions53:59 – Future Partnership Shakeups56:22 – Why Some Partnerships Actually Work01:00:44 – Missing James Ignatowich in the Scene01:01:36 – Competition vs Personality in Pickleball01:02:12 – Sponsorship Money & Paddle Deals01:05:55 – Lighting Issues During Matches01:06:38 – PPA 500 Tournament RecapWebsite: https://www.tylerloong.com/ KOTC All Accesshttps://www.youtube.com/channel/UCDiH-sjthLCovD8i79-AkWg/joinCode “KOTC” for insane discounts at: https://www.clubpickleballmastermind.com/kotc Use Code "KOTC" for Big Savings on Vulcan Gear: https://vulcansportinggoods.com/pagesKOTC Merch - Use “KOTC” kitchpickleball.comNEW KOTC DISCORD https://discord.com/invite/kNR65mBemfNEW KOTC CAMEOhttps://www.cameo.com/morekotcInstagram: Tyler's IG - @tyler.loong Jimmy's IG - @jimmymiller_pbKOTC IG - @morekingofthecourt Facebook: / tyler.loong --Support the show
Danni Elle Townsend didn't plan on becoming a pro pickleball player… Now she's the #3 overall pick in MLP, playing for the defending champion Columbus Sliders. We sat down with Danni LIVE at the Atlanta National Pickleball Club to talk about her journey from Australia to the biggest stage in pickleball—and what it's actually like stepping into Major League Pickleball as a rookie. In this episode, we get into: How Danni went from casually playing to going pro Making the move from Australia to the U.S. Getting drafted to the Columbus Sliders The pressure of joining a championship team What surprised her most about MLP Rookie life, team dynamics, and behind-the-scenes moments Plus plenty of classic PicklePod chaos If you want to understand where the next wave of pro talent is coming from—this is the episode. Be the first to try Zane's new course here: https://tzpickleball.com/ Check out Zane's Pro Pickleball Talk channel on Discord: https://discord.gg/wzNVADmZb #Pickleball #PPATour #PickleballPodcast Leave your voicemail for the PicklePod at (512) 200 - 4299 ------------------ Like the ep? Do us a favor: subscribe to our channel and leave a review on Apple or Spotify -Subscribe to our 'all things pickleball' *free e-newsletter* at https://www.thedink.beehiiv.com https://www.instagram.com/thedinkpickleball/ -Follow us on IG -Continue the convo in our private FB Group: https://www.facebook.com/groups/thedi... -For everything else we do, visit https://linktr.ee/dinkfam -Read more about Zane and subscribe to his newsletter at https://zanenavratilpickleball.com/ -Follow Zane on IG @zanenavratilpickleball #pickleball #pickleballcourts ------------------ 0:00 Intro 1:12 Australian roots 4:42 An illustrious table tennis career 9:05 Training for table tennis in Japan 12:59 How does table tennis convert to pickleball 23:04 Pro pickleball decathlon 27:52 Players in Asia living on moneyball tournaments 31:16 Does pickleball require more skill or athleticism? 35:47 Should blowing the ball be legal? 39:33 Danni + Zane challenge the rules 43:19 Known for playing loud and trash-talking 47:42 How Danni deals with pressure 45:10 Working with a coach 1:01:27 Nerding out on Star Wars Learn more about your ad choices. Visit megaphone.fm/adchoices
HOLY WRESTLING SHOWS!!!!Become a supporter of this podcast: https://www.spreaker.com/podcast/nsc-wrestling-and-gaming-podcast--4855340/support.
My dudes! You've seen him on Mystery Wrestling, Ring Of Honor, Maple Leaf Wrestling and more, but today I sit down bodyslam enthusiast and diagnosed piece of shit, Psycho Mike. In a long conversation that allowed my to nerd out, we talk about comedy wrestling, his time in wXw, MLP, and the elusive Wrestling Retribution Project! A must listen.Mike can be found on social media at:Instagram: https://www.instagram.com/iampsychomikeFacebook: https://www.facebook.com/psychomikerollinsTwitter: https://x.com/iAmPsychoMikeWe're on social media onFacebook: www.facebook.com/confusionwretlingpodcastTwitter, Bluesky, & Instagram: @thenovaofcass.All the other links can be found at www.linktr.ee/confusionwrestlingpodcast.If you'd like to assist monetarily, there's a tip jar at www.ko-fi.com/cassonova. For more bang for your buck, check out www.patreon.com/cassonova. For as little as $2, you can get the podcast two days early and ad free. You also get weekly exclusives and early access while helping upgrade the equipment. So be like Keith Winn, Alainya, and Alan Schroeder and check it out!Also, for all your energy drink and workout needs, head to www.reppsports.com and when you checkout, use my coupon code "CASS" at checkout and earn 15% off your order.Oh! And I'm on Cameo now at https://www.cameo.com/thenovaofcassAffiliate Links:Gevi: gevi.pxf.io/AWJxbxPrince Nana Coffee: https://princenanacoffee.com/?ref=ROBKAMERERGet your Tees at: https://www.teepublic.com/user/confusionwrestlingpodcastFor business inquiries, send all messages to rzkamerer[at]comcast.net.
Shotzi Blackheart is a fearless, high-risk competitor known for her punk-rock persona, neon green hair, and signature tank entrance. After making her mark in WWE, she's been thriving on the independent scene, reminding fans why she's one of the most unique and unpredictable performers in wrestling today. In the newest “Casual Conversations with The Classic” episode, The Wrestling Classic Justin chats with Shotzi Blackheart. They discuss her journey from WWE to dominating the independent scene, her upcoming matches in MLP and House of Glory, stepping in the ring with Charlie (fka Dakota Kai), chasing the Indie God title, and her creative freedom outside WWE, along with her love for horror, personal growth, and more. Enjoy!My Official Website + Demo Reel - https://www.justindhillon.com Instagram - https://www.instagram.com/thewrestlingclassic/ TikTok - https://www.tiktok.com/@thewrestlingclassic X - https://x.com/twcworldwide Youtube - https://www.youtube.com/@TheWrestlingClassic/ Limited Edition TWC Tee https://headquartersclothing.com/products/headquarters-x-the-wrestling-classic-logo-tee?_pos=1&_psq=wrestlinhg&_ss=e&_v=1.0 WWE Shop Affiliate wwe-shop.sjv.io/RGRxQv 500 Level https://www.500level.com/ Join the Discord Community https://linktr.ee/thewrestlingclassic All Episodes are on "The Wrestling Classic" Youtube Channel https://www.youtube.com/channel/UCOQOYraeFlX-xd8f3adQtTw#Shotzi #IndependentWrestling #WWE #ShotziBlackheart #ProWrestlingBecome a supporter of this podcast: https://www.spreaker.com/podcast/twc-show--4417554/support.
Join SP3, Miss Krssi Luv, Tru Draw Josh & Top Guy JJ for an all-new edition of our flagship podcast Tru Heel Heat 374 discussing the latest wrestling news including: TIME STAMPS: 0:00 SP3 cold open 3:21 Intro 7:00 SP3 & Miss Krssi Luv welcome you to the show 9:40 Is Mania worse than last year? / Why Jelly Roll? /Jade/Rhea promo & Cody/Orton brawl sucked 14:47 Top Guy JJ joins the show 21:26 Teacher embezzles money to go to WWE shows / Harlem runs in / WrestleMania issues / Nobody cares about Jelly Roll? 36:41 Is this the most thrown together WrestleMania ever? / Happy Birthday shoutouts 39:38 Tru Draw Josh joins the show 41:54 Who do you feel worse for losing gold before WrestleMania: Drew McIntyre or Carmelo Hayes? / Tru Heel Roll Call 48:58 AEW Dynamite & Collision: Slam Dunk Sunday recaps ft. Kenny Omega vs MJF announced 1:02:29 AEW ratings success w/ highest viewership in 2 years / AEW Revolution PPV success part 2 & Double Or Nothing ticket sales 1:07:31 Who deserves the most credit for AEW's hot streak? MJF, AEW World Title picture, year worth of quality TV & PPVs or big data adjustment for Nielsen? 1:18:22 Praise for MJF as AEW World Champion / interweaving stories in AEW brings success 1:37:25 MJF vs Kenny Omega announced for Dynasty & ticket sales for the PPV 1:40:11 Who will dethrone MJF for the AEW World Title: Kenny Omega or Will Ospreay? 1:51:17 Chris Jericho update / will Jericho return to AEW? 2:00:49 Ronda Rousey in AEW update / Ronda's FU to TKO at Revolution 2:09:53 Thekla re-signs w/AEW / Timeless Toni Storm original plans 2;19:25 More AEW news - Kyle O'Reilly & Bandido updates, Lio Rush Blackheart, MyAEW & more 2:25:00 ROH TV on Honor Club & ROH x MLP Global Wars recaps / ROH Supercard of Honor announced & MLP gets a TV deal 2:30:29 NJPW Road to Sakura Genesis recaps / Will Ospreay announced for Sakura Genesis / CMLL Martes Populares & Viernes Espectacular 2:33:39 TIK TOK TIME - THH Flashback to Krssi's debut & TH Funhouse 2:53:55 WWE SmackDown recap ft. Randy Orton dropping Jelly Roll & Sami Zayn wins US Title 3:07:41 It should be a 3 Way w/Sami, Trick & Melo at Mania? / Is HHH the problem? 3:11:10 Krssi's message to hardcore WWE fans during this Mania season 3:13:07 WWE Raw on Netflix recap ft. Roman/Punk/Usos drama 3:31:48 Seth Rollins & Paul Heyman anti chemistry / SP3 unmask parody of Seth 3:36:43 More WWE news - WrestleMania 42 ticket sales & planned matches, Bianca Belair & GUNTHER updates & more 3:54:05 WWE NXT, Evolve, TNA IMPACT & Sacrifice recaps / Steve Maclin update 4:02:17 Best, Worst, Moments & Matches of the Week 4:07:27 NJPW Sakura Genesis predictions 4:10:57 Outro Like, share, comment and subscribe to support! #WWE #AEW #NJPW #CMLL #TNA #ROH #MLP #MJF #ChrisJericho #SamiZayn #CarmeloHayes #SmackDown #WrestleMania Welcome to the Tru Heel Heat Wrestling YouTube channel where we cover the sport of professional wrestling including all WWE TV shows (Raw, Smackdown, & NXT), AEW Dynamite/Dark, IMPACT Wrestling, NJPW, ROH, Dark Side of the Ring and more. Our weekly podcast hosted by SP3, Top Guy JJ & Miss Krssi Luv breaking down the weekly wrestling news and present unfiltered, honest thoughts and opinions for wrestling fans by wrestling fans, drops every Saturday. We also include PPV reviews, countdowns, and exclusive interviews with wrestlers from all promotions hosted by a wide range of personalities such as Romeo, Chris G, Ness, StatKing, Drunk Guy JJ, J-News and more. Subscribe and enable ALL notifications to stay posted for the latest wrestling WWE news, highlights, commentary, updates and more.Become a member of Tru Heels Facebook community: www.facebook.com/groups/1336177103130224/Subscribe to Tru Heel Heat on YouTube: www.youtube.com/channel/UC0AmFQmsRyQYPKyRm5hDwNgFollow Tru Heels on Twitter: twitter.com/truheelheatFollow Tru Heels on Instagram: www.instagram.com/truheelheat/Music composed by JPM
Turnbuckle Tavern is powered by G FUEL—the zero-sugar, zero-crash energy formula built for late nights, gaming, and your daily grind. Save 20% with code TAVERN at GFUEL.com. Fuel up and keep it Tavern. We're also powered by the Official Dick Lazer—a USB-C rechargeable multi-function pen with a red-dot laser, flashlight, blacklight, and a signature gag feature. Perfect for pranks and parties. Head to DickLazers.com, use code TAVERN for 20% off, and keep it Tavern. Episode 176 centers on a week where real-life disruption and storyline momentum collided across the wrestling landscape. We start with TNA Sacrifice 2026, where the main event between Mike Santana and Steve Maclin was stopped early due to a legitimate injury, immediately destabilizing the world title picture heading into Rebellion. Eddie Edwards' involvement shifted the finish into an angle, but the bigger story is the uncertainty now at the top of the card. Elsewhere on the show, Leon Slater retained the X-Division Championship in a decisive performance, while Mustafa Ali and Tasha Steelz vs. Trey Miguel and Jada Stone stood out despite interference shaping the result. Across the board, strong in-ring work was consistently influenced by outside factors rather than clean resolution. TNA also introduced 21-year-old Ricky Sosa, a high-upside international prospect, in a segment grounded by Chris Bey's real-life recovery story. We then shift to Global Wars, where ROH and Maple Leaf Pro delivered meaningful crossover momentum. The Good Brothers became inaugural MLP Tag Team Champions, followed by Bishop Dyer turning on Kaito Kiyomiya, while the promotion also announced a new weekly TV deal launching in July. That momentum takes a hit with Josh Alexander confirming a severe knee injury and upcoming surgery, leaving no timetable for return and forcing adjustments across AEW, TNA, and MLP. We also break down Kyle Fletcher's comments about AEW All In stirring internal reaction, highlighting the balance between personal frustration and locker room perspective when injuries impact major moments. On the business side, ESPN has moved to intervene in the WWE PLE lawsuit, aiming to push the case into arbitration, while WrestleMania 42 ticket sales show a more aggressive discount-driven approach despite strong projected attendance. Plus, Sami Zayn forces his way onto the WrestleMania card by winning the United States Championship and setting up a defense against Trick Williams, Chris Jericho files a new "Cornerstone" trademark, Toni Storm's absence shifts into a mystery angle, and NJPW begins rolling out the Best of the Super Juniors field. Be sure to support the show and join our Patreon for just $2.99 a month for exclusive content at Patreon.com/TheTurnbuckleTavern. Follow us on social media @TurnbuckleTavern for all the latest updates. Until the following week, when we wine and dine with you kings and queens—stay out of the alley and away from the pork and beans. Good luck and good speed.
Wai Ting and Neal Flanagan review WWE SmackDown with Randy Orton vs. Matt Cardona, Sami Zayn answering Carmelo Hayes' US Open Challenge, The Bellas vs. Charlotte Flair & Alexa Bliss, Jelly Roll vs. Kit Wilson, Giulia vs. Tiffany Stratton, and more matches made for WrestleMania.They also discuss Steve Maclin's injury abruptly ending TNA Sacrifice's main event.XL: Wai & Neal discuss Josh Alexander's pending surgery, MLP's new TSN deal, Ospreay's NJPW return, US Netflix's price increase, “Kill Tony: WrestleMania” expectations, and more.The XL Edition continues at POSTwrestlingCafe.com with News of the Day and Feedback, ad-free.Orlando Wiet passes away at 60Josh Alexander set for surgeryMLP Mayhem TSN TV deal announced for JulyROH Supercard of Honor 2026 date & locationOspreay will wrestle at Sakura GenesisUS Netflix prices to rise; AEW Plus UpdateDavid Sahadi denies stalking charges‘Kill Tony: WrestleMania' will air on delayBad News Brown for WWE HoF Legacy WingSteve Maclin injury ends TNA Sacrifice main event (in the free edition)POST Wrestling Café Schedule:Friday: Daredevil Born Again - Season 2 premiere Friday: Rewind-A-SmackDown XLSaturday: TNA Sacrifice ReviewSaturday: Collision CourseFREE Shows:Friday: Rewind-A-SmackDownPhoto Courtesy: WWERASD Theme by THE IDENTiTY CRiSiS: theidentitycrisis.com / youtube.com/theidcAd Inquiries: info@truenativemedia.comBluesky: https://bsky.app/profile/postwrestling.comX: http://www.twitter.com/POSTwrestlingInstagram: http://www.instagram.com/POSTwrestlingFacebook: http://www.facebook.com/POSTwrestlingYouTube: http://www.youtube.com/POSTwrestlingSubscribe: https://postwrestling.com/subscribePatreon: http://postwrestlingcafe.comForum: https://forum.postwrestling.comDiscord: https://postwrestling.com/discordSee Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
ROH/MLP Global Wars Canada, Kenny Omega vs Swerve Strickland 2 | Grapsody 3/28/26 Grapsody ROH/MLP Global Wars Canada! Phil and Reg will also discuss Kenny Omega vs. Swerve Strickland 2, and more! Tune in for the latest news in the world of Pro Wrestling! – #ROHMLP Global Wars Canada – #KennyOmega vs #SwerveStrickland II – #SamiZayn winning the #WWE United States title – #AEW & WWE News, & much more Save now on the perfect gift with Aura Frames! Get $35 off Carver Mat at https://on.auraframes.com/FIGHTFUL. Use the promo code FIGHTFUL at check out! Want your question or statement read on the show? Donate a HumperChat at HumperChat.com or leave a SUPERCHAT in the YouTube Chat. (Click on the “$” located to the right at the bottom of the chatbox) To directly support us and our continuing breaking news, interviews, and the like, subscribe to FightfulSelect.com. You'll get exclusive news sent to you directly before anyone else, and dozens of podcasts monthly, including Sean Ross Sapp's Q&A, Ask Grapsody, Alex Pawlowski's Sour Graps, exclusive access to Fightful interviews, and more for only $5.99 a month or $64 a year! Fightful.com and Fightful Wrestling bring you accurate wrestling news, exclusive interviews, and podcasts in a professional but entertaining setting. We've interviewed the most prominent names across WWE, AEW, TNA, NJPW, UFC, and more! Make sure to check out Fightful Overbooked. The ESPN 2 version of Fightful! / fightfuloverbooked. Also, visit our clips channel at / fightfulscraps Shop our awesome merch! Shop.Fightful.com Follow Fightful on Social Media! X: @Fightful X: @FightfulSelect Tiktok: fightful.com Facebook: fightfulonline Instagram: fightfulonline Threads: @fightfulonline Bluesky: fightful.com Fightful Espanol Espanol Facebook: https://www.facebook.com/profile.php?… Espanol Instagram: / fightful_espanol Espanol Twitter: https://x.com/fightfulespanol Hosted by Simplecast, an AdsWizz company. See https://pcm.adswizz.com for information about our collection and use of personal data for advertising.
© 2020-2026 Ivy Podcast Discovery LLC
