Podcasts about tp1

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

Épisode simple et utile. Dans cet épisode, je donne mes instructions concernant les principales évaluations du cours Éthique et professionnalisme. Les critères de correction des forums de discussions et du TP1 y seront plus abondamment et plus explicitement abordés. Évaluations expliquées: Forums de discussion Travaux d'équipes TP1 TP2 Utilisation prudente des IA génératives Examen 1 Examen 2 Questionnaires formatifs Bonne écoute!

Dans ce débrief du week-end de Pâques, Xavier fait le point complet sur une semaine agitée, dominée par la guerre en Iran et ses répercussions directes sur les marchés. Au programme : le discours contradictoire de Trump depuis la Maison-Blanche, l'ultimatum du 6 avril sur le détroit d'Ormuz, l'envolée du pétrole à 112$, la FED coincée entre inflation et récession, et les premières destructions d'emploi aux États-Unis liées au conflit. Xavier partage aussi ses trades en live : son positionnement sur l'or (TP1 atteint, TP2 quasi touché), ses ventes sur le CAC stoppées net par une news de jeudi, et son analyse sur les indices américains qui tentent un rebond technique sans conviction. On parle aussi de Tesla (livraisons décevantes, problème de demande), de Sony qui augmente le prix de la PS5 à 650$, et d'Oracle qui licencie 20 à 30 000 personnes pour financer ses data centers IA. La semaine prochaine s'annonce explosive : ultimatum iranien le 6 avril, chiffres NFP, inflation de mars, marchés fermés lundi. Xavier donne ses clés pour naviguer dans ce contexte de volatilité extrême, avec une seule obsession : rester progressif, ne pas surréagir, et laisser passer les trains qu'on ne comprend pas. Hébergé par Acast. Visitez acast.com/privacy pour plus d'informations.

Épisode simple et utile. Dans cet épisode, je donne mes instructions concernant les principales évaluations du cours Éthique et professionnalisme. Les critères de correction des forums de discussions et du TP1 y seront plus abondamment et plus explicitement abordés. Évaluations expliquées: Forums de discussion Travaux d'équipes TP1 TP2 Utilisation prudente des IA génératives Examen 1 Examen 2 Questionnaires formatifs Bonne écoute!

Bonjour à tous,vous connaissez les polarités, la direction privilégiée pour les positions, le plan du jour S&P500 tant que sous 6780, les indices faibles/forts etc... alors ce matin, je fais plutot le focus sur l'inflation US de 14h30.... même si je rappelle AUSSI qu'il y a la BCE à 14h15 avec des taux attendus inchangés + le discours de Lagarde à 14h45.

Épisode simple et utile. Dans cet épisode, je donne mes instructions concernant les principales évaluations du cours Éthique et professionnalisme. Les critères de correction des forums de discussions et du TP1 y seront plus abondamment et plus explicitement abordés. Évaluations expliquées: Forums de discussion Travaux d'équipes TP1 TP2 Utilisation prudente des IA génératives Examen 1 Examen 2 Questionnaires formatifs Bonne écoute!

On this weeks TOTAP, your 100% Unofficial Cork City FC PodcastNeal Horgan joins us to talk about the 2005 anniversary nightThe ORC leaves us but TP1 is here in his placeDecky has a reminder for his fans in the WhatsApp groups The Emotion is too much for one AmigoThe Mailbag is open & Much Much More

Épisode simple et utile. Dans cet épisode, je donne mes instructions concernant les principales évaluations du cours Éthique et professionnalisme. Les critères de correction des forums de discussions et du TP1 y seront plus abondamment et plus explicitement abordés. Évaluations expliquées: Forums de discussion Travaux d'équipes TP1 TP2 Utilisation prudente des IA génératives Examen 1 Examen 2 Questionnaires formatifs Bonne écoute!

Ce matin, débrief :

Épisode simple et utile. Dans cet épisode, je donne mes instructions concernant les principales évaluations du cours Éthique et professionnalisme. Les critères de correction des forums de discussions et du TP1 y seront plus abondamment et plus explicitement abordés. Évaluations expliquées: Forums de discussion Travaux d'équipes TP1 TP2 Utilisation prudente des IA génératives Examen 1 Examen 2 Questionnaires formatifs Bonne écoute!

Épisode plate, mais simple et utile. Dans cet épisode, je donne mes instructions concernant les principales évaluations du cours Éthique et professionnalisme. Les critères de correction des forums de discussions et du TP1 y seront plus abondamment et plus explicitement abordés. Évaluations expliquées: Forums de discussion Travaux d'équipes TP1 TP2 Examen 1 Examen 2 Questionnaires formatifs Bonne écoute!

Épisode plate, mais simple et utile. Dans cet épisode, je donne mes instructions concernant les principales évaluations du cours Éthique et professionnalisme. Les critères de correction des forums de discussions et du TP1 y seront plus abondamment et plus explicitement abordés. Évaluations expliquées: Forums de discussion Travaux d'équipes TP1 TP2 Examen 1 Examen 2 Questionnaires formatifs Bonne écoute!

Deuxième podcast de la semaine 2 (module 2). Dans cet épisode, j'explique notamment ce que vous devez faire pour réussir votre TP1. Je donne également quelques autres instructions concernant les principales évaluations du cours Éthique et professionnalisme: Forums de discussion Travaux d'équipes TP1 TP2 Examen 1 Examen 2 Questionnaires formatifs Bonne écoute!

Deuxième partie du podcast de la semaine 2 (module 2). Dans cet épisode, j'explique notamment ce que vous devez faire et réaliser pour résussir votre TP1. Je donne également quelques autres instruction concernant les principales évaluations du cours Éthique et professionnalisme: Forums de discussion Travaux d'équipes TP1 TP2 Examen 1 Examen 2 Questionnaires formatifs Bonne écoute!

Fredrik och Ulf ger sig tillbaka i tiden till poddens start och jämför åsikter och insikter med nutid. Fölster har dykt djupare i ämnet små rörförstärkare. I veckans pryl provar vi en rördriven pedal från Hällelec som heter TP1. I detta avsnitt: Collings, Gibson, Frank Brothers, Gustavsson, Chase Bliss, Morningstar, Line6, Valley Arts, Fender, Hällelec, Swart, Benson.

1月15日早上6點多，我們與雲林縣野鳥學會鳥友李怡嬋老師於大埤鄉公所前會合，坐上車，開始沿途尋找大埤鄉TP1樣區的農田是否有小辮鴴的蹤影。 雲林鳥會鳥友李怡嬋使用雙筒望遠鏡，觀察道路旁的農田是否有小辮鴴棲息。 不只雲林縣大埤鄉，這天早上全台各地的鳥友同步進行小辮鴴普查，實際參與調查的志工共179位，創歷年參與志工數新高。最終統計全國觀察到11,231隻小辮鴴，也突破往年紀錄。小辮鴴在每年11月至隔年2、3月來到台灣過冬，有將近八成族群集中在雲林縣。因為牠們喜歡在花生田棲息覓食，所以被暱稱為「土豆鳥」。為了瞭解來台過冬的小辮鴴數量與族群分布，雲林縣野鳥學會與特有生物研究中心於每年1月舉辦「小辮鴴普查」活動，號召全國志工擔任調查員、認領樣區，協助完成普查。2023年總共有50個樣區進行調查，雲林縣17個鄉鎮共38個樣區，其中大埤鄉分成TP1、TP2兩個樣區。因面積廣闊，要在一個早上就調查完畢，必須開車或騎車才有辦法；加上小辮鴴警覺性高，對接近的人車都保持高度的警覺，所以調查員大多是開車，於車上進行觀察。這一天李怡嬋老師坐在副駕，和駕駛一同用雙眼掃描道路兩側的農田，尋找小辮鴴。車子沿著去年的調查路線行駛，以緩慢的速度，在廣袤的農田間穿梭。 發現小辮鴴後，志工調查員必須在紀錄表上登錄觀察時間、數量、小辮鴴的行為、使用的棲地類型、經緯度座標等資料。 如果發現了小辮鴴的身影，調查員會進一步以雙筒望遠鏡觀察、計算數量，並在調查紙紀錄下觀察時間、數量、小辮鴴的行為（覓食或休息）、使用的棲地類型（旱田、水田、有無作物等）、經緯度座標等資料，以便後續進行分析。在普查活動進行的當下，雲林縣元長國小的活動中心也非常熱鬧，不只設置了闖關遊戲，元長國小的同學為民眾進行小辮鴴介紹。元長國小校長王曉萍更大力支持普查活動，不僅將深入觀察小辮鴴列為校訂課程，更和李佳潤老師共同帶領學生到農田實際觀察小辮鴴。 雲林縣元長國小提供活動中心協助小辮鴴普查，活動當天許多家長帶著孩子前來參與。 王曉萍校長指出，元長國小學生有大約一半家裡務農，透過課程，不只可以讓同學深化對家鄉元長這塊土地的認識，也可以讓孩子將保育的觀念帶到家裡面，朝友善、有機農業邁進。本集讓我們繼續回顧今年的土豆鳥普查活動，感受冬天雲林的農田風景。 元長國小六年級同學創作小辮鴴紙雕，最後選出柯佑翰同學的作品（照片右下）成為2023年的土豆鳥大集合紀念章圖案。 李宥怡、吳羽暘、涂育萱等同學戴上可愛的小辮鴴帽，為民眾進行小辮鴴導覽介紹。 農人駕駛耕耘機，翻過的土地，吸引了一群鷺科鳥類尋找食物。看似蕭瑟的冬日景觀，其實蘊藏著豐沛的生命力。

1月15日早上6點多，我們與雲林縣野鳥學會鳥友李怡嬋老師於大埤鄉公所前會合，坐上車，開始沿途尋找大埤鄉TP1樣區的農田是否有小辮鴴的蹤影。 雲林鳥會鳥友李怡嬋使用雙筒望遠鏡，觀察道路旁的農田是否有小辮鴴棲息。 不只雲林縣大埤鄉，這天早上全台各地的鳥友同步進行小辮鴴普查，實際參與調查的志工共179位，創歷年參與志工數新高。最終統計全國觀察到11,231隻小辮鴴，也突破往年紀錄。小辮鴴在每年11月至隔年2、3月來到台灣過冬，有將近八成族群集中在雲林縣。因為牠們喜歡在花生田棲息覓食，所以被暱稱為「土豆鳥」。為了瞭解來台過冬的小辮鴴數量與族群分布，雲林縣野鳥學會與特有生物研究中心於每年1月舉辦「小辮鴴普查」活動，號召全國志工擔任調查員、認領樣區，協助完成普查。2023年總共有50個樣區進行調查，雲林縣17個鄉鎮共38個樣區，其中大埤鄉分成TP1、TP2兩個樣區。因面積廣闊，要在一個早上就調查完畢，必須開車或騎車才有辦法；加上小辮鴴警覺性高，對接近的人車都保持高度的警覺，所以調查員大多是開車，於車上進行觀察。這一天李怡嬋老師坐在副駕，和駕駛一同用雙眼掃描道路兩側的農田，尋找小辮鴴。車子沿著去年的調查路線行駛，以緩慢的速度，在廣袤的農田間穿梭。 發現小辮鴴後，志工調查員必須在紀錄表上登錄觀察時間、數量、小辮鴴的行為、使用的棲地類型、經緯度座標等資料。 如果發現了小辮鴴的身影，調查員會進一步以雙筒望遠鏡觀察、計算數量，並在調查紙紀錄下觀察時間、數量、小辮鴴的行為（覓食或休息）、使用的棲地類型（旱田、水田、有無作物等）、經緯度座標等資料，以便後續進行分析。在普查活動進行的當下，雲林縣元長國小的活動中心也非常熱鬧，不只設置了闖關遊戲，元長國小的同學為民眾進行小辮鴴介紹。元長國小校長王曉萍更大力支持普查活動，不僅將深入觀察小辮鴴列為校訂課程，更和李佳潤老師共同帶領學生到農田實際觀察小辮鴴。 雲林縣元長國小提供活動中心協助小辮鴴普查，活動當天許多家長帶著孩子前來參與。 王曉萍校長指出，元長國小學生有大約一半家裡務農，透過課程，不只可以讓同學深化對家鄉元長這塊土地的認識，也可以讓孩子將保育的觀念帶到家裡面，朝友善、有機農業邁進。本集讓我們繼續回顧今年的土豆鳥普查活動，感受冬天雲林的農田風景。 元長國小六年級同學創作小辮鴴紙雕，最後選出柯佑翰同學的作品（照片右下）成為2023年的土豆鳥大集合紀念章圖案。 李宥怡、吳羽暘、涂育萱等同學戴上可愛的小辮鴴帽，為民眾進行小辮鴴導覽介紹。 農人駕駛耕耘機，翻過的土地，吸引了一群鷺科鳥類尋找食物。看似蕭瑟的冬日景觀，其實蘊藏著豐沛的生命力。

Dieter Rams to twórca wielu nieśmiertelnych ikon wzornictwa. Do najbardziej znanych projektów należą gramofon SK4, radio z gramofonem TP1, oraz system półek Vitsœ 606. Poza tym jest autorem 10 zasad dobrego designu, które każdy projektant powinien znać.Materiał do tego podcastu został opracowany na podstawie filmu Garyego Hustwita Rams z 2018 roku.Muzyka wykorzystana w odcinku: morning glow by foxxy mulderr | https://www.foxxymulderr.com Music promoted by https://www.free-stock-music.com Attribution 4.0 International (CC BY 4.0) https://creativecommons.org/licenses/by/4.0/Zdjęcie wykorzystane w grafice: https://commons.wikimedia.org/wiki/File:Designer-Dieter_Rams.jpg Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0): https://creativecommons.org/licenses/by-sa/3.0/deed.en Zmiany dokonane w pierwotnym utworze: wycięte tło i zmiana nasycenia

Juan Martín Herrero, piloto sanrafaelino que compite en la categoría TP1.4 del Zonal Cuyano

Dans cet épisode, courte réflexion à propos d'un retour possible (libre et optionnel) en classe. Explications sommaires des TP1 et TP2. Courte introduction au module 4 et, surtout, à la grille d'analyse que vous aurez à utiliser pour résoudre votre problème éthique: la grille de Legault! Pour appliquer cette grille, nous étudierons le cas «Karen Duhamel» que nous avons déjà exploré au module 1. Bonne écoute! Objectifs du module 4: de nommer et d'expliquer les principales étapes de la «Grille d'analyse de Legault» et ses principales composantes de nommer et expliquer les étapes et sous étapes d'une analyse approfondie d'un dilemme éthique d'utiliser un outil d'analyse approfondie de problèmes éthiques pour résoudre des problèmes se produisant dans un cadre professionnel (TP2) d'expliquer et d'intégrer les notions de risque et de gestion de risques éthiques dans la résolution d'un problème éthique; de nommer et expliquer les problèmes éthiques les plus communs associés à la notion de risque éthique.

C'est l'automne. Avez-vous remarqué les couleurs dans les arbres? À Québec, c'est très «oranges»! On craint le rouge. De toute façon, ce sera blanc partout bientôt. Winter is coming, indeed. Plus sérieusement, votre TP1 est déposé. Bravo. Maintenant il faut résoudre le problème soumis. Dans cet épisode, vous aurez une courte introduction au module 4 et, surtout, à la grille d'analyse que vous aurez à utiliser pour résoudre votre problème éthique: la grille de Legault! Bonne écoute! Objectifs du module 4: de nommer et d'expliquer les principales étapes de la «Grille d'analyse de Legault» et ses principales composantes de nommer et expliquer les étapes et sous étapes d'une analyse approfondie d'un dilemme éthique d'utiliser un outil d'analyse approfondie de problèmes éthiques pour résoudre des problèmes se produisant dans un cadre professionnel (TP2) d'expliquer et d'intégrer les notions de risque et de gestion de risques éthiques dans la résolution d'un problème éthique; de nommer et expliquer les problèmes éthiques les plus communs associés à la notion de risque éthique.  

Introduction aux modules 4 et 5. Et explications du TP1. Objectifs du module 4: de nommer et d'expliquer les principales étapes de la «Grille d'analyse de Legault» et ses principales composantes de nommer et expliquer les étapes et sous étapes d'une analyse approfondie d'un dilemme éthique d'utiliser un outil d'analyse approfondie de problèmes éthiques pour résoudre des problèmes se produisant dans un cadre professionnel (TP2) d'expliquer et d'intégrer les notions de risque et de gestion de risques éthiques dans la résolution d'un problème éthique; de nommer et expliquer les problèmes éthiques les plus communs associés à la notion de risque éthique. Objectifs du module 5: d'expliquer comment, historiquement, les ordres professionnels se sont constitués au Québec; d'identifier les principaux jalons de l'histoire du professionnalisme au Québec de distinguer les différents modèles de professionnels et d'ordres professionnels qui ont été promus au cours de l'histoire du professionnalisme au Québec.  

Dean couldn't get permission to come and play... Tarver had to work... But Mark is back from vacation and is in the War Room So we shot some guns and invited the Bob and Dude Bolish over to join us... we talk guns...Dude gives us her take on the ladies class she attended...and we talk about the TP1...

FOREX Signal για το GBPUSD, Τετάρτη 23/05/18 @20:02 BUY@1.3414 SL@1.3297 TP1@1.3513 TP2@1.3563 Time-Frame Εισόδου : M15 ΠΡΟΣΟΧΗ : Το επίπεδο εισόδου είναι υποθετικό. Μην δώσετε PENDING ORDER. Η τιμή μπορεί να πυροδοτήσει την PENDING ORDER μ’ ενα spike (ακίδα) και κατόπιν να κινηθεί προς την αντίθετη κατεύθυνση χτυπώντας το SL!!! ΠΕΡΙΜΕΝΕΤΕ ΝΑ ΔΕΙΤΕ ΟΛΑ ΤΑ ΚΡΙΤΗΡΙΑ ΝΑ ΠΛΗΡΟΥΝΤΑΙ!!!! Δείτε το VIDEO για λεπτομερείς οδηγίες! Καλά Pips! Σοφία

FOREX Signal για το USDJPY, Τετάρτη 23/05/18 @21:38 SELL@109.80 SL@111.41 TP1@108.48 TP2@107.65 Time-Frame Εισόδου : H1 ΠΡΟΣΟΧΗ : Το επίπεδο εισόδου είναι υποθετικό. Μην δώσετε PENDING ORDER. Η τιμή μπορεί να πυροδοτήσει την PENDING ORDER μ’ ενα spike (ακίδα) και κατόπιν να κινηθεί προς την αντίθετη κατεύθυνση χτυπώντας το SL!!! ΠΕΡΙΜΕΝΕΤΕ ΝΑ ΔΕΙΤΕ ΟΛΑ ΤΑ ΚΡΙΤΗΡΙΑ ΝΑ ΠΛΗΡΟΥΝΤΑΙ!!!! Δείτε το VIDEO για λεπτομερείς οδηγίες! Καλά Pips! Σοφία

FOREX Signal για το EURUSD, Τετάρτη 23/05/18 @18:16 BUY@1.1772 SL@1.1683 TP1@1.1838 TP2@1.1904 TP3@1.1951 Time-Frame Εισόδου : M15 ΠΡΟΣΟΧΗ : Το επίπεδο εισόδου είναι υποθετικό. Μην δώσετε PENDING ORDER. Η τιμή μπορεί να πυροδοτήσει την PENDING ORDER μ’ ενα spike (ακίδα) και κατόπιν να κινηθεί προς την αντίθετη κατεύθυνση χτυπώντας το SL!!! ΠΕΡΙΜΕΝΕΤΕ ΝΑ ΔΕΙΤΕ ΟΛΑ ΤΑ ΚΡΙΤΗΡΙΑ ΝΑ ΠΛΗΡΟΥΝΤΑΙ!!!! Δείτε το VIDEO για λεπτομερείς οδηγίες! Καλά Pips! Σοφία

FOREX Signal για το USDCAD, Πέμπτη 05/04/18 @11:09 SELL@1.2730 SL@1.2917 (ή SL@1.2867 αν όλα τα κριτήρια εισόδου πληρούνται) TP1@1.2598 TP2@1.2357 Time-Frame Εισόδου : Η1 ΠΡΟΣΟΧΗ : Το επίπεδο εισόδου είναι υποθετικό. Μην δώσετε PENDING ORDER. Η τιμή μπορεί να πυροδοτήσει την PENDING ORDER μ’ ενα spike (ακίδα) και κατόπιν να κινηθεί προς την αντίθετη κατεύθυνση χτυπώντας το SL!!! ΠΕΡΙΜΕΝΕΤΕ ΝΑ ΔΕΙΤΕ ΟΛΑ ΤΑ ΚΡΙΤΗΡΙΑ ΝΑ ΠΛΗΡΟΥΝΤΑΙ!!!! Δείτε το VIDEO για λεπτομερείς οδηγίες! Καλά Pips! Σοφία

FOREX Signal για το EURUSD, Δευτέρα 02/04/18 @13:05 BUY@1.2370 SL@1.2282 TP1@1.2434 TP2@1.2517 TP3@1.2592 Time-Frame Εισόδου : Η1 ΠΡΟΣΟΧΗ : Το επίπεδο εισόδου είναι υποθετικό. Μην δώσετε PENDING ORDER. Η τιμή μπορεί να πυροδοτήσει την PENDING ORDER μ’ ενα spike (ακίδα) και κατόπιν να κινηθεί προς την αντίθετη κατεύθυνση χτυπώντας το SL!!! ΠΕΡΙΜΕΝΕΤΕ ΝΑ ΔΕΙΤΕ ΟΛΑ ΤΑ ΚΡΙΤΗΡΙΑ ΝΑ ΠΛΗΡΟΥΝΤΑΙ!!!! Δείτε το VIDEO για λεπτομερείς οδηγίες! Καλά Pips! Σοφία

FOREX Signal για το EURCAD, Δευτέρα 26/03/18 @09:16 SELL@1.5784 SL@1.5997 TP1@1.5638 ΤP2@1.5533 TP3@1.5463 TP4@1.5406 Time-Frame Εισόδου : Η1 ΠΡΟΣΟΧΗ : Το επίπεδο εισόδου είναι υποθετικό. Μην δώσετε PENDING ORDER. Η τιμή μπορεί να πυροδοτήσει την PENDING ORDER μ’ ενα spike (ακίδα) και κατόπιν να κινηθεί προς την αντίθετη κατεύθυνση χτυπώντας το SL!!! ΠΕΡΙΜΕΝΕΤΕ ΝΑ ΔΕΙΤΕ ΟΛΑ ΤΑ ΚΡΙΤΗΡΙΑ ΝΑ ΠΛΗΡΟΥΝΤΑΙ!!!! Δείτε το VIDEO για λεπτομερείς οδηγίες! Καλά Pips! Σοφία

FOREX SIGNAL για το AUDUSD, Τετάρτη 21/03/18 @13:26 ΣΕΝΑΡΙΟ ΑΓΟΡΑΣ BUY@0.7751 SL@0.7636 TP1@0.7819 TP2@0.7903 TP3@0.8057 ΣΕΝΑΡΙΟ ΠΩΛΗΣΗΣ SELL@0.7624 SL@0.7755 TP@0.7525 Time-Frame Εισόδου : Η1 ΠΡΟΣΟΧΗ : Το επίπεδο εισόδου είναι υποθετικό. Μην δώσετε PENDING ORDER. Η τιμή μπορεί να πυροδοτήσει την PENDING ORDER μ’ ενα spike (ακίδα) και κατόπιν να κινηθεί προς την αντίθετη κατεύθυνση χτυπώντας το SL!!! ΠΕΡΙΜΕΝΕΤΕ ΝΑ ΔΕΙΤΕ ΟΛΑ ΤΑ ΚΡΙΤΗΡΙΑ ΝΑ ΠΛΗΡΟΥΝΤΑΙ!!!! Δείτε το VIDEO για λεπτομερείς οδηγίες! Καλά Pips! Σοφία

FOREX Signal στο EURUSD, Δευτέρα 05/03/18 @12:33 ΣΕΝΑΡΙΟ ΑΓΟΡΑΣ BUY@1.2366 SL@1.2232 TP1@1.2470 TP2@1.2557 TP3@1.2677 Time-Frame Εισόδου : H1 ΣΕΝΑΡΙΟ ΠΩΛΗΣΗΣ SELL@1.2202 SL@1.2356 TP1@1.2062 TP2@1.1717 Time-Frame Εισόδου : M30 ΠΡΟΣΟΧΗ : Το επίπεδο εισόδου είναι υποθετικό. Μην δώσετε PENDING ORDER. Η τιμή μπορεί να πυροδοτήσει την PENDING ORDER μ’ ενα spike (ακίδα) και κατόπιν να κινηθεί προς την αντίθετη κατεύθυνση χτυπώντας το SL!!! ΠΕΡΙΜΕΝΕΤΕ ΝΑ ΔΕΙΤΕ ΟΛΑ ΤΑ ΚΡΙΤΗΡΙΑ ΝΑ ΠΛΗΡΟΥΝΤΑΙ!!!! Δείτε το VIDEO για λεπτομερείς οδηγίες! Καλά Pips! Σοφία

FOREX Signal on NZDUSD, Friday 02/03/18 @10:31 GMT BUY SCENARIO BUY@0.7293 SL@0.7181 TP@0.7392 SELL SCENARIO SELL@0.7172 SL@0.7289 TP1@0.7095 TP2@0.6859 Entry Time-Frame : H1 ATTENTION : Entry Level is hypothetical. DON'T PLACE PENDING ORDER. Price may trigger your Pending Order with a Spike and then move to the opposite direction hitting your SL!!!! WAIT FOR THE CRITERIA TO BE MET!!!! View VIDEO for details! Happy Pips! Sofia

FOREX Signal για το NZDUSD, Παρασκευή 02/03/18 @10:24 ΣΕΝΑΡΙΟ ΑΓΟΡΑΣ BUY@0.7293 SL@0.7181 TP@0.7392 ΣΕΝΑΡΙΟ ΠΩΛΗΣΗΣ SELL@0.7172 SL@0.7289 TP1@0.7095 TP2@0.6859 Time-Frame Εισόδου : H1 ΠΡΟΣΟΧΗ : Το επίπεδο εισόδου είναι υποθετικό. Μην δώσετε PENDING ORDER. Η τιμή μπορεί να πυροδοτήσει την PENDING ORDER μ’ ενα spike (ακίδα) και κατόπιν να κινηθεί προς την αντίθετη κατεύθυνση χτυπώντας το SL!!! ΠΕΡΙΜΕΝΕΤΕ ΝΑ ΔΕΙΤΕ ΟΛΑ ΤΑ ΚΡΙΤΗΡΙΑ ΝΑ ΠΛΗΡΟΥΝΤΑΙ!!!! Δείτε το VIDEO για λεπτομερείς οδηγίες! Καλά Pips! Σοφία

FOREX Signal για το AUDUSD, Παρασκευή 02/03/18 @14:40 ΣΕΝΑΡΙΟ ΑΓΟΡΑΣ BUY@0.7826 SL@0.7699 TP1@0.7947 TP2@0.8055 ΣΕΝΑΡΙΟ ΠΩΛΗΣΗΣ SELL@0.7690 SL@0.7817 TP@0.7533 Time-Frame Εισόδου : H1 ΠΡΟΣΟΧΗ : Το επίπεδο εισόδου είναι υποθετικό. Μην δώσετε PENDING ORDER. Η τιμή μπορεί να πυροδοτήσει την PENDING ORDER μ’ ενα spike (ακίδα) και κατόπιν να κινηθεί προς την αντίθετη κατεύθυνση χτυπώντας το SL!!! ΠΕΡΙΜΕΝΕΤΕ ΝΑ ΔΕΙΤΕ ΟΛΑ ΤΑ ΚΡΙΤΗΡΙΑ ΝΑ ΠΛΗΡΟΥΝΤΑΙ!!!! Δείτε το VIDEO για λεπτομερείς οδηγίες! Καλά Pips! Σοφία

FOREX Signal στο USDJPY, Δευτέρα 19/02/18 @12:23 SELL@105.52 SL@106.98 TP1@104.01 TP2@102.51 ....Ή.... BUY@107.09 SL@105.50 TP1@108.29 TP2@110.01 Time-Frame Εισόδου : H1 Time-Frame Παρακολούθησης/Διαχείρισης : H1 ΠΡΟΣΟΧΗ : Το επίπεδο εισόδου είναι υποθετικό. Μην δώσετε PENDING ORDER. Η τιμή μπορεί να πυροδοτήσει την PENDING ORDER μ’ ενα spike (ακίδα) και κατόπιν να κινηθεί προς την αντίθετη κατεύθυνση χτυπώντας το SL!!! ΠΕΡΙΜΕΝΕΤΕ ΝΑ ΔΕΙΤΕ ΟΛΑ ΤΑ ΚΡΙΤΗΡΙΑ ΝΑ ΠΛΗΡΟΥΝΤΑΙ!!!! Δείτε το VIDEO για λεπτομερείς οδηγίες! Καλά Pips! Σοφία

EURCAD, Tuesday 13/02/18 @18:26 GMT SELL@1.5393 SL@1.5602 TP1@1.5153 TP2@1.5075 Entry Time-Frame : H1 ATTENTION : Entry Level is hypothetical. DON'T PLACE PENDING ORDER. Price may trigger your Pending Order with a Spike and then move to the opposite direction hitting your SL!!!! WAIT FOR THE CRITERIA TO BE MET!!!! View VIDEO for details! Happy Pips! Sofia

CADJPY, Tuesday 13/02/18 @18:55 GMT BUY@86.32 SL@85.15 TP1@87.44 TP2@89.12 Entry Time-Frame : M30 ATTENTION : Entry Level is hypothetical. DON'T PLACE PENDING ORDER. Price may trigger your Pending Order with a Spike and then move to the opposite direction hitting your SL!!!! WAIT FOR THE CRITERIA TO BE MET!!!! View VIDEO for details! Happy Pips! Sofia

EURGBP, Tuesday 13/02/18 @09:09 GMT SELL SCENARIO SELL@0.8787 SL@0.8907 TP@0.8345 Entry Time-Frame : H1 BUY SCENARIO BUY@0.8900 SL@0.8861 TP1@0.8963 TP2@0.8986 Entry Time-Frame : M30

FOREX Signal on EURGBP, Thursday 23/11/17 @16:50 GMT SELL@0.8841 SL@0.8915 TP1@0.8760 TP2@0.8694 TP3@0.8588 Entry Time-Frame : H1 TF ATTENTION : Entry Level is hypothetical. DON'T PLACE PENDING ORDER. Price may trigger your Pending Order with a Spike and then move to the opposite direction hitting your SL!!!! WAIT FOR THE CRITERIA TO BE MET!!!! View VIDEO for details! Happy Pips! Sofia

FOREX Signal στο EURUSD SELL@1.1748 SL@1.1867 TP1@1.1625 TP2@1.1587 TP3@1.1552 TP4@1.1452 TP5@1.1227 Time-Frame Εισόδου : M30 ΠΡΟΣΟΧΗ : Το επίπεδο εισόδου είναι υποθετικό. Μην δώσετε PENDING ORDER. Η τιμή μπορεί να πυροδοτήσει την PENDING ORDER μ' ενα spike (ακίδα) και κατόπιν να κινηθεί προς την αντίθετη κατεύθυνση χτυπώντας το SL!!! ΠΕΡΙΜΕΝΕΤΕ ΝΑ ΔΕΙΤΕ ΟΛΑ ΤΑ ΚΡΙΤΗΡΙΑ ΝΑ ΠΛΗΡΟΥΝΤΑΙ!!!! View VIDEO for details! Happy Pips! Sofia

FOREX Signal on AUDCAD, Monday 16/10/17 @14:44 GMT SELL@0.9797 SL@0.9887 TP1@0.9707 TP2@0.9539 Entry Time-Frame : M30 View VIDEO for details! Happy Pips! Sofia

FOREX SIGNAL για το EURUSD, Δευτέρα 22/05/17 @12:25 SELL@1.1118 SL@1.1217 TP1@1.0969 TP2@1.0914 TP3@1.0763 Time-Frame Εισόδου : M30 Δείτε το VIDEO για λεπτομέρειες! Καλά Pips! Σοφία

FOREX Signal για το EURUSD Αφού βεβαιωθείτε οτι πληρούνται όλα τα κριτήρια Εισόδου που περιγράφονται στο VIDEO : BUY@1.0683 SL@1.0595 TP1@1.0810 TP2@1.0928 ....OR.... SELL@1.0587 SL@1.0679 TP1@1.0490 TP2@1.0404 TP3@1.0357 Time-Frame Εισόδου : H1 Παρακολουθήστε το VIDEO για λεπτομέρειες! Καλά Pips! Σοφία

Αφού βεβαιωθείτε οτι πληρούνται όλα τα κριτήρια Εισόδου που περιγράφονται στο VIDEO : BUY@1.2259 SL@1.2151 TP1@1.2375 TP2@1.2575 ....OR.... SELL@1.2100 SL@1.2244 TP1@1.1929 TP2@1.1604 Time-Frame Εισόδου : H1 Παρακολουθήστε το VIDEO για λεπτομέρειες! Καλά Pips! Σοφία

Αφού βεβαιωθείτε οτι πληρούνται όλα τα κριτήρια Εισόδου που περιγράφονται στο VIDEO : SELL@120.30 SL@121.21 TP1@118.75 TP2@117.31 TP3@115.53 .....OR.... BUY@121.29 SL@120.30 TP1@123.13 TP2@124.17 TP3@125.50 Time-Frame Εισόδου : H1 Παρακολουθήστε το VIDEO για λεπτομέρειες! Καλά Pips! Σοφία

SELL@0.8465 SL@0.8544 TP1@0.8323 TP2@0.8253 TP3@0.8119 TP4@0.7970 .... OR.... BUY@0.8551 SL@0.8470 TP@0.8620 Entry Time-Frame : H1 View VIDEO for details! Happy Pips! Sofia

SELL@1.0500 SL@1.0578 TP1@1.0325 TP2@0.9852 Time-Frame Εισόδου : Μ30 Παρακολουθήστε το VIDEO για λεπτομέρειες! Δώστε ιδιαίτερη προσοχή στη ΜΕΛΕΤΗ του ΣΥΜΜΕΤΡΙΚΟΥ ΤΡΙΓΩΝΟΥ στο Μηνιαίο Χάρτη!!!! Το EURUSD αναμένεται να πέσει άλλα 2660pips που σημαίνει οτι θα φτάσει στο επίπεδο 0.7840 Καλά Pips! Σοφία Σταυροπούλου

After ALL CRITERIA mentioned on the VIDEO are met, SELL@0.7174 SL@0.7239 TP1@0.7057 TP2@0.6898 ....OR.... BUY@0.7254 SL@0.7176 TP1@0.7485 TP2@0.7672 Entry Time-Frame : H1 View VIDEO for details! Happy Pips! Sofia

Αφού βεβαιωθείτε οτι πληρούνται όλα τα κριτήρια Εισόδου που περιγράφονται στο VIDEO : SELL@1234.88 SL@1244.20 TP1@1219.99 TP2@1213.61 TP3@1189.16 Time-Frame Εισόδου : Μ30 Παρακολουθήστε το VIDEO για λεπτομέρειες! Καλά Pips! Σοφία

BUY@1.0530 SL@1.0398 TP1@1.0752 TP2@1.0853 TP3@1.0924 .....Ή... SELL@1.0349 SL@1.0520 TP@0.9804 Time-Frame Εισόδου : H4 Δείτε το VIDEO για λεπτομέρειες. Καλά Pips! Σοφία

BUY@0.6954 SL@0.6898 TP@0.7057 ..... OR... SELL@0.6879 SL@0.6949 TP1@0.6730 TP2@0.6316 Entry Time-Frame : M30 View VIDEO for details! Happy Pips! Sofia

BUY@16.76 SL@16.57 TP1@17.11 TP2@17.35 TP3@17.69 Entry Time-Frame : M30 Monitor the pair from M30 TF and trail your SL 80-90pips below each new Kijun Sen (ICHIMOKU Blue Line) plateau (flat level). View VIDEO for details! Happy Pips! Sofia

SELL@1.2328 SL@1.2455 TP@1.2115 ......OR.... BUY@1.2482 SL@1.2347 TP1@1.2661 TP2@1.2852 Entry Time-Frame : M30 Monitor the pair from H1 TF and trail your SL 60pips above each new Kijun Sen (ICHIMOKU Blue Line) plateau (flat level) if SELL is triggered or below each new Kijun Sen plateau if BUY is triggered. View VIDEO for details! Happy Pips! Sofia

SELL@0.8524 SL@0.8637 TP1@0.8229 TP2@0.8122 TP3@0.7784 Entry Time-Frame : H1 Monitor the pair from H1 TF and trail your SL 65pips above each new Kijun Sen (ICHIMOKU Blue Line) plateau (flat level). View VIDEO for details! Happy Pips! Sofia

BUY@0.7610 SL@0.7528 TP1@0.7731 TP2@0.7911 ....(Το επίπεδο Αγοράς είναι ΕΝΔΕΙΚΤΙΚΟ. Βεβαιωθείτε οτι όλα τα Κριτήρια Εισόδου πληρούνται πριν μπείτε. Μην δώσετε PENDING ORDER.) Παρακολουθήστε το ζευγάρι από το H4 Time Frame. Σύρετε το SL σας 35pips κάτω από κάθε νέο επίπεδο της Kijun Sen που είναι η μπλε γραμμή του ICHIMOKU. Δείτε το VIDEO για τις λεπτομέρειες. Καλά Pips! Σοφία

BUY@115.86 SL@114.29 TP1@119.91 TP2@121.68 TP3@125.94 ....(Το επίπεδο Αγοράς είναι ΕΝΔΕΙΚΤΙΚΟ. Βεβαιωθείτε οτι όλα τα Κριτήρια Εισόδου πληρούνται πριν μπείτε. Μην δώσετε PENDING ORDER.) Παρακολουθήστε το ζευγάρι από το Η4 Time Frame. Σύρετε το SL σας 80pips κάτω από κάθε νέο επίπεδο της Kijun Sen που είναι η μπλε γραμμή του ICHIMOKU. Δείτε το VIDEO για τις λεπτομέρειες. Καλά Pips! Σοφία