Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

An H100 GPU can run 10^15 FLOPs/s. But somehow, a model like Gemini Flash-Lite is stuck at 200 tokens/s. These numbers show just how much of a bottleneck memory bandwidth is. In this video, we look at how LLMs are evolving to work around this limitation. Thanks Inception for... show more

Julia Turc

17,492 subscribers

25,821 görüntüleme • 4 ay önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

GPU tradeoff series: A100 is not much more powerful than 4090 🫠 GPU Perf and Price: - 4090: 330 fp16 TFLOPs, $1,749 - A100 (80GB): 312 fp16 TFLOPs, $20,000 > A100 is 11.4X more pricy Training speed for GPT-2(124M) with llm.c: - 4090: 153K tokens/s - A100 (80GB): 195K tokens/s > A100 is only 1.3X faster (both trained using a single card, A100 llm.c training is shown in the video, 4090 video is in the quoted tweet) Conclusion: 4090 has a much better cost vs performance ratio Why: As in the H100 vs. 4090 comparison, the biggest difference between A100 and 4090 is their GPU memory size/bandwidth and cross-GPU communication bandwidth, which does not matter too much if your model can fit into a single 4090. Specs: 4090: - GPU memory size: 24GB - memory bandwidth: 1 TB/s - communication bandwidth: 64 GB/s A100: - GPU memory size: 80GB - memory bandwidth: 2 TB/s - communication bandwidth: 900 GB/s Nvidia killed off NVLink (a high-speed communication link that connects GPUs) on 4090. (Jensen Huang smiling face) If multiple 4090s could be interconnected via NVLink, their performance would be closer to datacenter-grade A100 GPUs, even for training larger models. Additionally, 4090 isn't allowed in datacenters, that's how Nvidia makes 💰💰💰

GPU tradeoff series: A100 is not much more powerful than 4090 🫠 GPU Perf and Price: - 4090: 330 fp16 TFLOPs, $1,749 - A100 (80GB): 312 fp16 TFLOPs, $20,000 > A100 is 11.4X more pricy Training speed for GPT-2(124M) with llm.c: - 4090: 153K tokens/s - A100 (80GB): 195K tokens/s > A100 is only 1.3X faster (both trained using a single card, A100 llm.c training is shown in the video, 4090 video is in the quoted tweet) Conclusion: 4090 has a much better cost vs performance ratio Why: As in the H100 vs. 4090 comparison, the biggest difference between A100 and 4090 is their GPU memory size/bandwidth and cross-GPU communication bandwidth, which does not matter too much if your model can fit into a single 4090. Specs: 4090: - GPU memory size: 24GB - memory bandwidth: 1 TB/s - communication bandwidth: 64 GB/s A100: - GPU memory size: 80GB - memory bandwidth: 2 TB/s - communication bandwidth: 900 GB/s Nvidia killed off NVLink (a high-speed communication link that connects GPUs) on 4090. (Jensen Huang smiling face) If multiple 4090s could be interconnected via NVLink, their performance would be closer to datacenter-grade A100 GPUs, even for training larger models. Additionally, 4090 isn't allowed in datacenters, that's how Nvidia makes 💰💰💰

Yuchen Jin

234,951 görüntüleme • 1 yıl önce

This is the fastest I've seen Llama 3.3 running anywhere! Llama 3.3 70B running at 652 t/s is lightning fast. And if you want Llama 3.1, here are the speeds I was able to get: • Llama 3.1 8B: 1006 t/s • Llama 3.1 70B: 709 t/s • Llama 3.1 405B: 206 t/s (You can access all of these models for free! See the link below.) This speed is incredible, but the interesting part is what's happening behind the scenes: These models aren't running on a GPU! In this video, I'm using the SambaNova cloud to access these models. They built a custom chip (SN40L) optimized for AI workflows. A single SN40L chip can hold hundreds of models (trillions of parameters) in memory! The speed alone is a huge deal, but the big advantage is for agentic workflows running multiple specialized models. A GPU can only host a single model and switch (unload and load) to a different model if necessary. An SN40L, on the other hand, can host every model at once, making it much faster. Here is the video where you can see how fast these chips are:

This is the fastest I've seen Llama 3.3 running anywhere! Llama 3.3 70B running at 652 t/s is lightning fast. And if you want Llama 3.1, here are the speeds I was able to get: • Llama 3.1 8B: 1006 t/s • Llama 3.1 70B: 709 t/s • Llama 3.1 405B: 206 t/s (You can access all of these models for free! See the link below.) This speed is incredible, but the interesting part is what's happening behind the scenes: These models aren't running on a GPU! In this video, I'm using the SambaNova cloud to access these models. They built a custom chip (SN40L) optimized for AI workflows. A single SN40L chip can hold hundreds of models (trillions of parameters) in memory! The speed alone is a huge deal, but the big advantage is for agentic workflows running multiple specialized models. A GPU can only host a single model and switch (unload and load) to a different model if necessary. An SN40L, on the other hand, can host every model at once, making it much faster. Here is the video where you can see how fast these chips are:

Santiago

97,505 görüntüleme • 1 yıl önce

I’m at a loss for words at how condescending this is towards women. Do the Dems think marriages are stuck in the 1950’s?

I’m at a loss for words at how condescending this is towards women. Do the Dems think marriages are stuck in the 1950’s?

Jean

22,429,089 görüntüleme • 1 yıl önce

If we get AGI before 2030 but can only produce ~200 GW a year of chips on advanced process nodes, can we ease the bottleneck by going back to older nodes? Some of the most singularity-pilled investors think so. Most of the FLOPS improvement between chip generations has come from numerics - not transistor density. But you could just design a new version of a 7nm chip like the A100 to have FP4. Holding numerics and die area constant, a B200 (2025 chip on 4nm) would only have ~3.5x more FLOPS than an A100 (2020 chip on 7nm). That seems like a manageable haircut - does it mean we can blow past the 200 GW ceiling? Dylan Patel explains why this is not an apples-to-apples comparison. If you run real-world performance analysis on DeepSeek V3 or Kimi K2.5, the performance gap between Hopper and Blackwell isn't 3x. It's ~20x. Why? Because inference is already memory-bandwidth-bound, and older chips have far fewer FLOPS per die, requiring even more communication between chips. Remember the bandwidth hierarchy: on-chip SRAM runs at tens of TB/s, HBM at single-digit TB/s, NVLink within a 72-GPU domain at high hundreds of GB/s, and between racks at low hundreds of GB/s. Each boundary is roughly a 10x drop. With less compute per chip, you need more chips to run the same model - which means more communication across those slower pipes that are already bottlenecking you.

If we get AGI before 2030 but can only produce ~200 GW a year of chips on advanced process nodes, can we ease the bottleneck by going back to older nodes? Some of the most singularity-pilled investors think so. Most of the FLOPS improvement between chip generations has come from numerics - not transistor density. But you could just design a new version of a 7nm chip like the A100 to have FP4. Holding numerics and die area constant, a B200 (2025 chip on 4nm) would only have ~3.5x more FLOPS than an A100 (2020 chip on 7nm). That seems like a manageable haircut - does it mean we can blow past the 200 GW ceiling? Dylan Patel explains why this is not an apples-to-apples comparison. If you run real-world performance analysis on DeepSeek V3 or Kimi K2.5, the performance gap between Hopper and Blackwell isn't 3x. It's ~20x. Why? Because inference is already memory-bandwidth-bound, and older chips have far fewer FLOPS per die, requiring even more communication between chips. Remember the bandwidth hierarchy: on-chip SRAM runs at tens of TB/s, HBM at single-digit TB/s, NVLink within a 72-GPU domain at high hundreds of GB/s, and between racks at low hundreds of GB/s. Each boundary is roughly a 10x drop. With less compute per chip, you need more chips to run the same model - which means more communication across those slower pipes that are already bottlenecking you.

Dwarkesh Patel

56,362 görüntüleme • 3 ay önce

DS4 running on DGX Spark (GB10 / CUDA), private branch for now. 12 tokens/sec, the memory bandwidth is limited in this system, at 270GB/sec. But prefill is ways more alighed to M3 Max at ~200 t/s. I'll release when more mature, but it is almost sure that it will get merged.

DS4 running on DGX Spark (GB10 / CUDA), private branch for now. 12 tokens/sec, the memory bandwidth is limited in this system, at 270GB/sec. But prefill is ways more alighed to M3 Max at ~200 t/s. I'll release when more mature, but it is almost sure that it will get merged.

antirez

83,448 görüntüleme • 2 ay önce

"Mac Minis for example are a very good fit" - Andrej Karpathy Andrej Karpathy shouted out my work on EXO Labs in his keynote at Y Combinator AI SUS! Here's the breakdown: Right now most AI workloads run in the cloud where requests from different users are continuously batched together. These workloads are FLOPS-bound and favors hardware with the best unit economics of $ per FLOP, i.e. enterprise GPUs. The personal computing revolution will shift these workloads to personal devices with lower batch sizes (mostly batch_size=1). batch_size=1 inference is memory-bound, because all of the model parameters need to be loaded into the GPU every time a token is generated. Apple Silicon with its Unified Memory architecture has a lot of memory and memory bandwidth per $ compared to other hardware: - M4 Pro Mac Mini, 24GB @ 273GB/s, $58.33/GB, $5.13/GB/s - H100, 80GB @ 3350GB/s, $625/GB, $14.93/GB/s The unit economics of Apple Silicon are becoming more compelling with every release of the Mac. The future of AI inference looks more like open weights models (OpenAI open weights model soonTM) run at low batch_size on personal devices.

"Mac Minis for example are a very good fit" - Andrej Karpathy Andrej Karpathy shouted out my work on EXO Labs in his keynote at Y Combinator AI SUS! Here's the breakdown: Right now most AI workloads run in the cloud where requests from different users are continuously batched together. These workloads are FLOPS-bound and favors hardware with the best unit economics of $ per FLOP, i.e. enterprise GPUs. The personal computing revolution will shift these workloads to personal devices with lower batch sizes (mostly batch_size=1). batch_size=1 inference is memory-bound, because all of the model parameters need to be loaded into the GPU every time a token is generated. Apple Silicon with its Unified Memory architecture has a lot of memory and memory bandwidth per $ compared to other hardware: - M4 Pro Mac Mini, 24GB @ 273GB/s, $58.33/GB, $5.13/GB/s - H100, 80GB @ 3350GB/s, $625/GB, $14.93/GB/s The unit economics of Apple Silicon are becoming more compelling with every release of the Mac. The future of AI inference looks more like open weights models (OpenAI open weights model soonTM) run at low batch_size on personal devices.

Alex Cheema

103,487 görüntüleme • 1 yıl önce

DeepSeek R1 671B is ridiculously good, but running at 158 tokens per second is something out of this world. A model *this good* running *this fast* is 3 years ahead of this time. The secret: DeepSeek in this short video isn't running on GPUs. It's running on custom-made chips! This is running on SambaNova and their SN40L chips, which are designed and optimized for running AI workflows. SambaNova is sponsoring my work. We designed GPUs to run games and later realized we could use them for AI. This is very different from creating a chip specifically for AI from the ground up. Just think about this for a second: One single SNL40 chip can simultaneously hold 100+ models (trillions of parameters) in memory! An agentic workflow that uses multiple models simultaneously won't need to swap models from memory even once! By the way, the Llama family of models *screams* on the SambaNova Cloud. Here are some numbers from my latest tests: • Llama 3.3 70B: 367.32 t/s • Llama 3.2 1B: 2381.82 t/s • Llama 3.2 3B: 1335.71 t/s • Llama 3.1 8B: 929.58 t/s • Llama 3.1 70B: 369.16 t/s • Llama 3.1 405B: 103.37 t/s You can access all of these models for free!

DeepSeek R1 671B is ridiculously good, but running at 158 tokens per second is something out of this world. A model this good running this fast is 3 years ahead of this time. The secret: DeepSeek in this short video isn't running on GPUs. It's running on custom-made chips! This is running on SambaNova and their SN40L chips, which are designed and optimized for running AI workflows. SambaNova is sponsoring my work. We designed GPUs to run games and later realized we could use them for AI. This is very different from creating a chip specifically for AI from the ground up. Just think about this for a second: One single SNL40 chip can simultaneously hold 100+ models (trillions of parameters) in memory! An agentic workflow that uses multiple models simultaneously won't need to swap models from memory even once! By the way, the Llama family of models screams on the SambaNova Cloud. Here are some numbers from my latest tests: • Llama 3.3 70B: 367.32 t/s • Llama 3.2 1B: 2381.82 t/s • Llama 3.2 3B: 1335.71 t/s • Llama 3.1 8B: 929.58 t/s • Llama 3.1 70B: 369.16 t/s • Llama 3.1 405B: 103.37 t/s You can access all of these models for free!

Santiago

130,934 görüntüleme • 1 yıl önce

PowerInfer - a high-speed inference engine for deploying LLMs locally. Just came across this super interesting project on speeding up inference. It's not MoE but it's a simple approach that exploits the high locality in LLM inference to design a GPU-CPU hybrid inference engine. Hot-activated neurons are preloaded onto the GPU for fast access, while cold-activated neurons (the majority) are computed on the CPU. This approach significantly reduces GPU memory demands and CPU-GPU data transfer. It achieves an average token generation rate of 13.20 tokens/s, with a peak of 29.08 tokens/s, across various LLMs on a single NVIDIA RTX 4090 GPU. It's on only 18% lower than that achieved by a top-tier server-grade A100 GPU. It also significantly outperforms llama.cpp by up to 11.69x while retaining model accuracy. There is a lot more innovation around inference that's coming fast. Really encouraged by the study on sparse computation to enhance the computational efficiency of LLMs. It's now possible to use PowerInfer with Llama 2 and Faclon 40B. Mistral-7B support is coming soon!

PowerInfer - a high-speed inference engine for deploying LLMs locally. Just came across this super interesting project on speeding up inference. It's not MoE but it's a simple approach that exploits the high locality in LLM inference to design a GPU-CPU hybrid inference engine. Hot-activated neurons are preloaded onto the GPU for fast access, while cold-activated neurons (the majority) are computed on the CPU. This approach significantly reduces GPU memory demands and CPU-GPU data transfer. It achieves an average token generation rate of 13.20 tokens/s, with a peak of 29.08 tokens/s, across various LLMs on a single NVIDIA RTX 4090 GPU. It's on only 18% lower than that achieved by a top-tier server-grade A100 GPU. It also significantly outperforms llama.cpp by up to 11.69x while retaining model accuracy. There is a lot more innovation around inference that's coming fast. Really encouraged by the study on sparse computation to enhance the computational efficiency of LLMs. It's now possible to use PowerInfer with Llama 2 and Faclon 40B. Mistral-7B support is coming soon!

elvis

261,622 görüntüleme • 2 yıl önce

Etched is deploying two new technologies in chip design: low-voltage inference and cluster-scale memory. CEO Gavin Uberti says they'll make their chips much more power-efficient and way, way faster than today's leading GPUs. He breaks it down: "We looked at a lot of early research directions, and we realized the key things that models need are way more compute and way faster memory." "If you think about inference, there are two key parts: prefill and decode. For prefill, it's a compute-bound problem. You need to have more FLOPS, more operations per second on each of your chips." "On our GPU, the bottleneck's actually thermals. You can't really run a GPU at more than around 50% of what it could theoretically do, or it'll melt." "So we're using a new technology today called low-voltage inference to try to solve this problem. You bring the voltage of the chip down dramatically, which allows us to have way, way better efficiency in terms of how much power is drawn per unit of math, and thus fit way way more flops onto the chip..." "For decode, it's all about bandwidth. Not just bandwidth on a chip, but bandwidth across your cluster. That's why we have this technology we call cluster-scale memory. It reduces the amount of time it takes to communicate from one chip to another dramatically." "As a result we can go use all of our HBM, HBM bandwidth, SRAM, SRAM bandwidth, and our scale-up domain as a single coherent pool. And that means if you're a user, you can go get much faster tokens per second, while still keeping your costs low."

Etched is deploying two new technologies in chip design: low-voltage inference and cluster-scale memory. CEO Gavin Uberti says they'll make their chips much more power-efficient and way, way faster than today's leading GPUs. He breaks it down: "We looked at a lot of early research directions, and we realized the key things that models need are way more compute and way faster memory." "If you think about inference, there are two key parts: prefill and decode. For prefill, it's a compute-bound problem. You need to have more FLOPS, more operations per second on each of your chips." "On our GPU, the bottleneck's actually thermals. You can't really run a GPU at more than around 50% of what it could theoretically do, or it'll melt." "So we're using a new technology today called low-voltage inference to try to solve this problem. You bring the voltage of the chip down dramatically, which allows us to have way, way better efficiency in terms of how much power is drawn per unit of math, and thus fit way way more flops onto the chip..." "For decode, it's all about bandwidth. Not just bandwidth on a chip, but bandwidth across your cluster. That's why we have this technology we call cluster-scale memory. It reduces the amount of time it takes to communicate from one chip to another dramatically." "As a result we can go use all of our HBM, HBM bandwidth, SRAM, SRAM bandwidth, and our scale-up domain as a single coherent pool. And that means if you're a user, you can go get much faster tokens per second, while still keeping your costs low."

TBPN

20,404 görüntüleme • 14 gün önce

Sharp question to S Jaishankar in Finland Question: Is India just stuck in the role of a frustrated observer in the Iran war? Is there much you can do? Jaishankar (smiling): I think at this point much of the world is stuck in the role of a frustrated observer

Sharp question to S Jaishankar in Finland Question: Is India just stuck in the role of a frustrated observer in the Iran war? Is there much you can do? Jaishankar (smiling): I think at this point much of the world is stuck in the role of a frustrated observer

Shashank Mattoo

54,140 görüntüleme • 1 ay önce

THE AI RACE IS OVER. DUST CLEARED. GROK 4 FAST ALREADY HIT 67 BILLION TOKENS Grok 4 Fast just bulldozed the leaderboard, clocking 67.1 billion tokens and leaving rivals gasping for bandwidth! Leaderboard Mode: • Qwen3’s 80B trails at 23B – miles behind • Gemini 2.5 Flash barely flickers in 3rd • Claude? Still waiting at the loading screen • TrustAI charts show Grok’s surge lighting up November It’s not just an AI model anymore – it’s a speed-run on the entire industry! Source: TrustAI, xAI, Medium

THE AI RACE IS OVER. DUST CLEARED. GROK 4 FAST ALREADY HIT 67 BILLION TOKENS Grok 4 Fast just bulldozed the leaderboard, clocking 67.1 billion tokens and leaving rivals gasping for bandwidth! Leaderboard Mode: • Qwen3’s 80B trails at 23B – miles behind • Gemini 2.5 Flash barely flickers in 3rd • Claude? Still waiting at the loading screen • TrustAI charts show Grok’s surge lighting up November It’s not just an AI model anymore – it’s a speed-run on the entire industry! Source: TrustAI, xAI, Medium

Mario Nawfal

196,729 görüntüleme • 8 ay önce

I had to test it myself to believe this unreal inference speed. 3,000 tokens/s for 1 user on standard datacenter GPUs. They leveraged a hidden efficiency gap in how GPUs generate tokens. Kog just achieved 3,000 tokens/s on 8× AMD MI300X GPUs and 2,100 on 8× NVIDIA H200 (FP16, no speculative decoding). Their tech preview is on a 2B model, and they show how their techniques will scale to large frontier MoE models at similar speeds. That's a huge number because normal low-batch GPU decoding for 2B to 8B models is usually closer to 100 to 300 tokens/s per request, so Kog is claiming something like a 10X to 30X jump in the speed one user actually feels. Their trick: they are getting the speed by treating LLM decoding as a memory streaming problem, not mainly a math problem. For 1 user at batch size 1, the GPU is not doing big, efficient matrix-matrix work like in training or large-batch serving; it is repeatedly pulling the model’s active weights from high-bandwidth memory for each new token, so speed depends on how smoothly those weights keep flowing. Normal inference stacks keep breaking that flow. They run many separate GPU programs for different parts of the model, move intermediate results through memory, wait at synchronization points, talk back to the CPU for scheduling or sampling, and then repeat this token after token. Kog’s answer is to co-design 3 things that are usually tuned separately: the runtime, the low-level GPU code, and the model architecture. The biggest engineering move is the monokernel, where the whole decode pass runs as 1 persistent GPU-resident program, including sampling, so the system does not keep stopping for kernel launches, CPU scheduling, and intermediate memory round trips. They also rebuilt synchronization, because their own measurements say grid sync was eating around 35% of token-generation time; instead of making every compute unit wait at a broad barrier, each unit waits only for the exact data it needs. On AMD MI300X, they also map memory access around the chiplet layout, because memory latency changes depending on which die makes the request. Then their Laneformer model uses Delayed Tensor Parallelism, which lets cross-GPU communication happen in the background instead of blocking every layer.

I had to test it myself to believe this unreal inference speed. 3,000 tokens/s for 1 user on standard datacenter GPUs. They leveraged a hidden efficiency gap in how GPUs generate tokens. Kog just achieved 3,000 tokens/s on 8× AMD MI300X GPUs and 2,100 on 8× NVIDIA H200 (FP16, no speculative decoding). Their tech preview is on a 2B model, and they show how their techniques will scale to large frontier MoE models at similar speeds. That's a huge number because normal low-batch GPU decoding for 2B to 8B models is usually closer to 100 to 300 tokens/s per request, so Kog is claiming something like a 10X to 30X jump in the speed one user actually feels. Their trick: they are getting the speed by treating LLM decoding as a memory streaming problem, not mainly a math problem. For 1 user at batch size 1, the GPU is not doing big, efficient matrix-matrix work like in training or large-batch serving; it is repeatedly pulling the model’s active weights from high-bandwidth memory for each new token, so speed depends on how smoothly those weights keep flowing. Normal inference stacks keep breaking that flow. They run many separate GPU programs for different parts of the model, move intermediate results through memory, wait at synchronization points, talk back to the CPU for scheduling or sampling, and then repeat this token after token. Kog’s answer is to co-design 3 things that are usually tuned separately: the runtime, the low-level GPU code, and the model architecture. The biggest engineering move is the monokernel, where the whole decode pass runs as 1 persistent GPU-resident program, including sampling, so the system does not keep stopping for kernel launches, CPU scheduling, and intermediate memory round trips. They also rebuilt synchronization, because their own measurements say grid sync was eating around 35% of token-generation time; instead of making every compute unit wait at a broad barrier, each unit waits only for the exact data it needs. On AMD MI300X, they also map memory access around the chiplet layout, because memory latency changes depending on which die makes the request. Then their Laneformer model uses Delayed Tensor Parallelism, which lets cross-GPU communication happen in the background instead of blocking every layer.

Rohan Paul

13,148 görüntüleme • 1 ay önce

I’m working at night look at how hard I work. Look how much work this is in my 250 hp Climate controlled Tesla. THANK ME FOR FEEDING THE WORLD. anyways, it is a nice night out. Hope this corn makes me a bunch of money.

I’m working at night look at how hard I work. Look how much work this is in my 250 hp Climate controlled Tesla. THANK ME FOR FEEDING THE WORLD. anyways, it is a nice night out. Hope this corn makes me a bunch of money.

Shay Foulk

20,658 görüntüleme • 2 ay önce

Joe Rogan & Jim Breuer Look Back at When We Had ‘Tall Biden’ For a Day “Look how long his f**king legs are. Look how tall he is. This is absolutely insane … It's like a guy doing an impression of Joe Biden … This guy's a basketball player. He can dunk.” 😂

Joe Rogan & Jim Breuer Look Back at When We Had ‘Tall Biden’ For a Day “Look how long his f**king legs are. Look how tall he is. This is absolutely insane … It's like a guy doing an impression of Joe Biden … This guy's a basketball player. He can dunk.” 😂

Chief Nerd

99,154 görüntüleme • 4 ay önce

Does anyone have a proper explanation for this scene? Because how in the actual fuck did they go from 1959's Hawkins High School straight into Henry's memory like that?? Ik this is a memory of henry but still how. Was he even there around that time !? 😭 #StrangerThings5

Does anyone have a proper explanation for this scene? Because how in the actual fuck did they go from 1959's Hawkins High School straight into Henry's memory like that?? Ik this is a memory of henry but still how. Was he even there around that time !? 😭 #StrangerThings5

Ceaser Wrestling

680,071 görüntüleme • 6 ay önce

DeepMind CEO Demis Hassabis says the AI bottleneck is already moving from model ideas to physical supply chains. "How much of the restriction at this point is physical? I am talking memory shortage, GPU shortage, and electricity." Demis: "That is constraining a lot of the deployment for sure. We see so much more demand for our models - Gemini and the other models that we have - than we can possibly serve." Then the less obvious part: "It does constrain a little bit the research, because you need a lot of chips to be able to experiment on new ideas at big enough scale that you can actually see if they are going to work." And on memory: "The whole supply chain is kind of strained... It still in the end actually comes down to a few suppliers of a few of the key components. Anywhere where there is some kind of constraint on the capacity, there is a sort of choke point." Important framing: The next AI race is not just who has the best model architecture. It is who can secure memory, chips, power, suppliers, and enough experimental capacity to find the next breakthrough before everyone else.

DeepMind CEO Demis Hassabis says the AI bottleneck is already moving from model ideas to physical supply chains. "How much of the restriction at this point is physical? I am talking memory shortage, GPU shortage, and electricity." Demis: "That is constraining a lot of the deployment for sure. We see so much more demand for our models - Gemini and the other models that we have - than we can possibly serve." Then the less obvious part: "It does constrain a little bit the research, because you need a lot of chips to be able to experiment on new ideas at big enough scale that you can actually see if they are going to work." And on memory: "The whole supply chain is kind of strained... It still in the end actually comes down to a few suppliers of a few of the key components. Anywhere where there is some kind of constraint on the capacity, there is a sort of choke point." Important framing: The next AI race is not just who has the best model architecture. It is who can secure memory, chips, power, suppliers, and enough experimental capacity to find the next breakthrough before everyone else.

Karl Mehta

25,716 görüntüleme • 18 gün önce

The era of 1-bit LLMs is here — now with WebGPU acceleration! 🤯 It's incredible to think that a quantized 1.7B model (just 290MB in size) can run at ~100 tokens per second entirely in your browser. Try the demo yourself 👇

The era of 1-bit LLMs is here — now with WebGPU acceleration! 🤯 It's incredible to think that a quantized 1.7B model (just 290MB in size) can run at ~100 tokens per second entirely in your browser. Try the demo yourself 👇

Xenova

105,316 görüntüleme • 3 ay önce

TWO BOXES THE SIZE OF A MAC MINI JUST RAN A 235 BILLION PARAMETER MODEL ON A DESK It is two NVIDIA DGX Spark units linked by a single cable. A year ago a model this size meant renting a GPU cluster by the hour. Now it sits next to your monitor for around $8,000. Here is the twist most people miss. Linking them does not create one shared 256GB memory pool. The model is split across both boxes, and that is the only reason a 235B model fits at all. It answers at roughly 10 tokens per second, and both chips sit at just 74 degrees while sipping around 50 watts. Every token stays on the desk. Nothing touches a cloud, and nothing leaves the room. The ceiling for what you can run at home just jumped from 70B to 235B. Bookmark this & Watch it run ↓

TWO BOXES THE SIZE OF A MAC MINI JUST RAN A 235 BILLION PARAMETER MODEL ON A DESK It is two NVIDIA DGX Spark units linked by a single cable. A year ago a model this size meant renting a GPU cluster by the hour. Now it sits next to your monitor for around $8,000. Here is the twist most people miss. Linking them does not create one shared 256GB memory pool. The model is split across both boxes, and that is the only reason a 235B model fits at all. It answers at roughly 10 tokens per second, and both chips sit at just 74 degrees while sipping around 50 watts. Every token stays on the desk. Nothing touches a cloud, and nothing leaves the room. The ceiling for what you can run at home just jumped from 70B to 235B. Bookmark this & Watch it run ↓

slash1s

101,133 görüntüleme • 1 ay önce