正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Attention is a lookup. Each token builds a query, compares it against every key in the sequence, and pulls value vectors weighted by the match. Stack that 96 layers deep and you get a frontier model. Video covers the full pipeline: Q/K/V, attention scores, encoder blocks.

tetsuo

235,722 subscribers

104,200 次观看 • 11 天前 •via X (Twitter)

艺术教育科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

[Self-Attention] by Hand ✍️ Self-attention is what enables LLMs to understand context. How does it work? This exercise demonstrates how to calculate a 6-3 attention head by hand. Note that if we have two instances of this, we get 6-6 attention (i.e., multi-head attention, n=2). -- 𝗚𝗼𝗮𝗹 -- Transform [6D Features 🟧] to [3D Attention Weighted Features 🟦] -- 𝗪𝗮𝗹𝗸𝘁𝗵𝗿𝗼𝘂𝗴𝗵 -- [1] Given ↳ A set of 4 feature vectors (6-D): x1,x2,x3,x4 [2] Query, Key, Value ↳ Multiply features x's with linear transformation matrices WQ, WK, and WV, to obtain query vectors (q1,q2,q3,q4), key vectors (k1,k2,k3,k4), and value vectors (v1,v2,v3,v4). ↳ "Self" refers to the fact that both queries and keys are derived from the same set of features. [3] 🟪 Prepare for MatMul ↳ Copy query vectors ↳ Copy the transpose of key vectors [4] 🟪 MatMul ↳ Multiply K^T and Q ↳ This is equivalent to taking dot product between every pair of query and key vectors. ↳ The purpose is to use dot product as an estimate of the "matching score" between every key-value pair. ↳ This estimate makes sense because dot product is the numerator of Cosine Similarity between two vectors. [5] 🟨 Scale ↳ Scale each element by the square root of dk, which is the dimension of key vectors (dk=3). ↳ The purpose is to normalize the impact of the dk on matching scores, even if we scale dk to 32, 64, or 128. ↳ To simplify hand calculation, we approximate [ □/sqrt(3) ] with [ floor(□/2) ]. [6] 🟩 Softmax: e^x ↳ Raise e to the power of the number in each cell ↳ To simplify hand calculation, we approximate e^□ with 3^□. [7] 🟩 Softmax: ∑ ↳ Sum across each column [8] 🟩 Softmax: 1 / sum ↳ For each column, divide each element by the column sum ↳ The purpose is normalize each column so that the numbers sum to 1. In other words, each column is a probability distribution of attention, and we have four of them. ↳ The result is the Attention Weight Matrix (A) (yellow) [9] 🟦 MatMul ↳ Multiply the value vectors (Vs) with the Attention Weight Matrix (A) ↳ The results are the attention weighted features Zs. ↳ They are fed to the position-wise feed forward network in the next layer.

[Self-Attention] by Hand ✍️ Self-attention is what enables LLMs to understand context. How does it work? This exercise demonstrates how to calculate a 6-3 attention head by hand. Note that if we have two instances of this, we get 6-6 attention (i.e., multi-head attention, n=2). -- 𝗚𝗼𝗮𝗹 -- Transform [6D Features 🟧] to [3D Attention Weighted Features 🟦] -- 𝗪𝗮𝗹𝗸𝘁𝗵𝗿𝗼𝘂𝗴𝗵 -- [1] Given ↳ A set of 4 feature vectors (6-D): x1,x2,x3,x4 [2] Query, Key, Value ↳ Multiply features x's with linear transformation matrices WQ, WK, and WV, to obtain query vectors (q1,q2,q3,q4), key vectors (k1,k2,k3,k4), and value vectors (v1,v2,v3,v4). ↳ "Self" refers to the fact that both queries and keys are derived from the same set of features. [3] 🟪 Prepare for MatMul ↳ Copy query vectors ↳ Copy the transpose of key vectors [4] 🟪 MatMul ↳ Multiply K^T and Q ↳ This is equivalent to taking dot product between every pair of query and key vectors. ↳ The purpose is to use dot product as an estimate of the "matching score" between every key-value pair. ↳ This estimate makes sense because dot product is the numerator of Cosine Similarity between two vectors. [5] 🟨 Scale ↳ Scale each element by the square root of dk, which is the dimension of key vectors (dk=3). ↳ The purpose is to normalize the impact of the dk on matching scores, even if we scale dk to 32, 64, or 128. ↳ To simplify hand calculation, we approximate [ □/sqrt(3) ] with [ floor(□/2) ]. [6] 🟩 Softmax: e^x ↳ Raise e to the power of the number in each cell ↳ To simplify hand calculation, we approximate e^□ with 3^□. [7] 🟩 Softmax: ∑ ↳ Sum across each column [8] 🟩 Softmax: 1 / sum ↳ For each column, divide each element by the column sum ↳ The purpose is normalize each column so that the numbers sum to 1. In other words, each column is a probability distribution of attention, and we have four of them. ↳ The result is the Attention Weight Matrix (A) (yellow) [9] 🟦 MatMul ↳ Multiply the value vectors (Vs) with the Attention Weight Matrix (A) ↳ The results are the attention weighted features Zs. ↳ They are fed to the position-wise feed forward network in the next layer.

Tom Yeh

101,010 次观看 • 2 年前

Scaled Dot-Product Attention by hand ✍️ I explained attention in my recent AI seminar as follows: Step 1 — Compare We take one token as a query and compare it against all keys using dot products. This gives us a grid of similarity scores: every query against every key. Step 2 — Scale We divide those scores by √dₖ to keep the values numerically stable. Step 3 — Normalize We apply softmax to turn raw scores into a probability distribution—values between 0 and 1 that sum to 1. These are the attention weights. Step 4 — Combine We use those weights to compute a weighted sum of the values. Each output token becomes a linear combination of all previous tokens—maybe 37% from one, 23% from another, and a little from the rest. No blackbox. Just dot products, scaling, softmax, and weighted sums—built one row at a time in Excel.

Scaled Dot-Product Attention by hand ✍️ I explained attention in my recent AI seminar as follows: Step 1 — Compare We take one token as a query and compare it against all keys using dot products. This gives us a grid of similarity scores: every query against every key. Step 2 — Scale We divide those scores by √dₖ to keep the values numerically stable. Step 3 — Normalize We apply softmax to turn raw scores into a probability distribution—values between 0 and 1 that sum to 1. These are the attention weights. Step 4 — Combine We use those weights to compute a weighted sum of the values. Each output token becomes a linear combination of all previous tokens—maybe 37% from one, 23% from another, and a little from the rest. No blackbox. Just dot products, scaling, softmax, and weighted sums—built one row at a time in Excel.

Tom Yeh

31,114 次观看 • 6 个月前

New short course: Attention in Transformers: Concepts and Code in PyTorch. Last week we released a course on how LLM transformers work. This week, go deeper and learn about the technical ideas behind the attention mechanism, and see how to code it in PyTorch. This course is built with Joshua Starmer, Founder and CEO of StatQuest. The attention mechanism was a breakthrough that led to transformers, the architecture powering large language models like ChatGPT. Transformers, introduced in the 2017 paper: "Attention is All You Need" by Viswani and others, took off because of its highly scalable design. In this course, you’ll learn how the attention mechanism, a key element of transformer-based LLMs, works and implement it in PyTorch. You'll develop deep intuition about building reliable, functional, and scalable AI applications. What you will do: - Understand the evolution of the attention mechanism, a key breakthrough that led to transformers. - Learn the relationships between word embeddings, positional embeddings, and attention. - Learn about the Query, Key, and Value matrices, and how to produce and use them in attention. - Walk through the math required to calculate self-attention and masked self-attention to learn why and how they work. - Understand the difference between self-attention and masked self-attention and how one is used in the encoder to build context-aware embeddings and the other is used in the decoder for generative outputs. - Learn the details of the encoder-decoder architecture, cross-attention, and multi-head attention and how they are all incorporated into a transformer. - Use PyTorch to code a class that implements self-attention, masked self-attention, and multi-head attention. There're lots of exciting technical details in this course. Please sign up here:

New short course: Attention in Transformers: Concepts and Code in PyTorch. Last week we released a course on how LLM transformers work. This week, go deeper and learn about the technical ideas behind the attention mechanism, and see how to code it in PyTorch. This course is built with Joshua Starmer, Founder and CEO of StatQuest. The attention mechanism was a breakthrough that led to transformers, the architecture powering large language models like ChatGPT. Transformers, introduced in the 2017 paper: "Attention is All You Need" by Viswani and others, took off because of its highly scalable design. In this course, you’ll learn how the attention mechanism, a key element of transformer-based LLMs, works and implement it in PyTorch. You'll develop deep intuition about building reliable, functional, and scalable AI applications. What you will do: - Understand the evolution of the attention mechanism, a key breakthrough that led to transformers. - Learn the relationships between word embeddings, positional embeddings, and attention. - Learn about the Query, Key, and Value matrices, and how to produce and use them in attention. - Walk through the math required to calculate self-attention and masked self-attention to learn why and how they work. - Understand the difference between self-attention and masked self-attention and how one is used in the encoder to build context-aware embeddings and the other is used in the decoder for generative outputs. - Learn the details of the encoder-decoder architecture, cross-attention, and multi-head attention and how they are all incorporated into a transformer. - Use PyTorch to code a class that implements self-attention, masked self-attention, and multi-head attention. There're lots of exciting technical details in this course. Please sign up here:

Andrew Ng

132,220 次观看 • 1 年前

🎉 Congrats to MiniMax (official) on releasing MiniMax M3! Frontier coding and agentic capabilities, native image and video input, computer use, and a 1M-token context window, all in a single open model. At the heart of M3 is MSA, a new sparse attention architecture: instead of attending densely over the full KV cache, each query scores 128-token KV blocks and runs attention only over the top blocks. That is what makes 1M-token context practical to serve. M3 runs in vLLM with day-0 support, verified on NVIDIA and AMD hardware: ✨ MSA sparse attention with dedicated prefill and decode kernels ✨ 1M-token context serving with prefix caching and chunked prefill ✨ BF16 and MXFP8 checkpoints, with MoE backends for both Hopper and Blackwell ✨ Native multimodal input (image + video) ✨ Tool calling, reasoning parsing, and thinking-mode control for agent workloads Day-0 support like this is a true team effort. Grateful to the teams at MiniMax (official), NVIDIA AI, AI at AMD, and Inferact, and to the vLLM community for making it happen. 🙏 Deep dive into the implementation, kernel work, and deployment recipes: 🔗

🎉 Congrats to MiniMax (official) on releasing MiniMax M3! Frontier coding and agentic capabilities, native image and video input, computer use, and a 1M-token context window, all in a single open model. At the heart of M3 is MSA, a new sparse attention architecture: instead of attending densely over the full KV cache, each query scores 128-token KV blocks and runs attention only over the top blocks. That is what makes 1M-token context practical to serve. M3 runs in vLLM with day-0 support, verified on NVIDIA and AMD hardware: ✨ MSA sparse attention with dedicated prefill and decode kernels ✨ 1M-token context serving with prefix caching and chunked prefill ✨ BF16 and MXFP8 checkpoints, with MoE backends for both Hopper and Blackwell ✨ Native multimodal input (image + video) ✨ Tool calling, reasoning parsing, and thinking-mode control for agent workloads Day-0 support like this is a true team effort. Grateful to the teams at MiniMax (official), NVIDIA AI, AI at AMD, and Inferact, and to the vLLM community for making it happen. 🙏 Deep dive into the implementation, kernel work, and deployment recipes: 🔗

vLLM

40,306 次观看 • 1 个月前

A tricky LLM interview question: You're serving a reasoning model on vLLM, and it keeps running out of GPU memory on long traces. So you add KV cache compression and evict 90% of the cached tokens. VRAM usage stays as is and GPU still runs out of memory. Why? (answer below) Evicting 90% of the KV cache can free almost none of the memory it was using. This sounds counterintuitive, but it follows directly from how production servers store the cache today. The KV cache grows with every token a model generates. Each token appends its key and value vectors across every layer, and nothing is freed while generation continues. This is the dominant memory cost for reasoning models. If a 32K-token CoT caches ~32K tokens of KV vectors, a Qwen3-32B with 4-bit weights will run out-of-memory around 24K tokens on a 24GB GPU. One obvious solution is to keep the important tokens and drop the rest, since attention is sparse enough to allow it. But this does not solve the memory problem yet. The reason is paged attention, which is the memory manager behind vLLM and most production servers. Under the hood, it splits GPU memory into fixed physical blocks, each one holds the KV for about 16 tokens. This block returns to the allocator only when every slot inside it is empty. Since the eviction logic selects tokens by importance, and such tokens are scattered across blocks... ...so despite eviction, almost every block is left with at least some survivor tokens. For instance, if the logic evicts 14k of 16k tokens across 1,000 blocks, most likely every block will still have a token. This means the allocator frees almost nothing. Placing the new tokens into those freed slots is not ideal because it breaks the cache's layout. Say token 16,001 arrives, and it's placed in the slot the 40th token used to hold. The cache now reads position 38, then 16,001, then 41, so the cache is no longer in token order. Attention can still compute the right answer from that, but only if every slot now carries a separate note recording which position it actually holds. This introduces another bookkeeping cost that an in-order layout inherently avoids. So the cache is logically 90% smaller and still physically the same size. Many compression results miss this because they measure on pre-allocated contiguous tensors rather than a paged server. There's another problem. Eviction methods pick which tokens to keep by looking at the attention scores themselves (as expected). But fast attention kernels used in production, like FlashAttention, never save those scores. They compute attention in small pieces and throw the full score grid away as they go, which is also why they're fast. So the exact signal eviction methods need isn't available in memory. The workaround is to fall back to eager attention and build the full matrix, which gives up the speed FlashAttention was there to provide. NVIDIA published a method called TriAttention to solve both these problems. It never needs attention scores. Instead, it scores tokens from the geometry of the model's key and query vectors before RoPE is applied, where those vectors sit in stable clusters. For the memory problem, it runs a compaction pass every 128 decoded tokens. The surviving tokens slide forward to close the holes eviction creates, so whole blocks empty out and return to the allocator while the cache stays in token order. On long reasoning traces, the approach matches full-attention accuracy while decoding 2.5x faster and using 10.7x less KV memory. KV cache compression is a big infrastructure problem. The number that decides whether it works is the count of freed blocks, not the count of evicted tokens. You can find the NVIDIA write-up here: I wrote a first-principles breakdown of how the KV cache works. It walks through why the model stores keys and values at all, why the cache grows with every token, and a comparison of LLM generation speed with and without KV caching. Read it below.

A tricky LLM interview question: You're serving a reasoning model on vLLM, and it keeps running out of GPU memory on long traces. So you add KV cache compression and evict 90% of the cached tokens. VRAM usage stays as is and GPU still runs out of memory. Why? (answer below) Evicting 90% of the KV cache can free almost none of the memory it was using. This sounds counterintuitive, but it follows directly from how production servers store the cache today. The KV cache grows with every token a model generates. Each token appends its key and value vectors across every layer, and nothing is freed while generation continues. This is the dominant memory cost for reasoning models. If a 32K-token CoT caches ~32K tokens of KV vectors, a Qwen3-32B with 4-bit weights will run out-of-memory around 24K tokens on a 24GB GPU. One obvious solution is to keep the important tokens and drop the rest, since attention is sparse enough to allow it. But this does not solve the memory problem yet. The reason is paged attention, which is the memory manager behind vLLM and most production servers. Under the hood, it splits GPU memory into fixed physical blocks, each one holds the KV for about 16 tokens. This block returns to the allocator only when every slot inside it is empty. Since the eviction logic selects tokens by importance, and such tokens are scattered across blocks... ...so despite eviction, almost every block is left with at least some survivor tokens. For instance, if the logic evicts 14k of 16k tokens across 1,000 blocks, most likely every block will still have a token. This means the allocator frees almost nothing. Placing the new tokens into those freed slots is not ideal because it breaks the cache's layout. Say token 16,001 arrives, and it's placed in the slot the 40th token used to hold. The cache now reads position 38, then 16,001, then 41, so the cache is no longer in token order. Attention can still compute the right answer from that, but only if every slot now carries a separate note recording which position it actually holds. This introduces another bookkeeping cost that an in-order layout inherently avoids. So the cache is logically 90% smaller and still physically the same size. Many compression results miss this because they measure on pre-allocated contiguous tensors rather than a paged server. There's another problem. Eviction methods pick which tokens to keep by looking at the attention scores themselves (as expected). But fast attention kernels used in production, like FlashAttention, never save those scores. They compute attention in small pieces and throw the full score grid away as they go, which is also why they're fast. So the exact signal eviction methods need isn't available in memory. The workaround is to fall back to eager attention and build the full matrix, which gives up the speed FlashAttention was there to provide. NVIDIA published a method called TriAttention to solve both these problems. It never needs attention scores. Instead, it scores tokens from the geometry of the model's key and query vectors before RoPE is applied, where those vectors sit in stable clusters. For the memory problem, it runs a compaction pass every 128 decoded tokens. The surviving tokens slide forward to close the holes eviction creates, so whole blocks empty out and return to the allocator while the cache stays in token order. On long reasoning traces, the approach matches full-attention accuracy while decoding 2.5x faster and using 10.7x less KV memory. KV cache compression is a big infrastructure problem. The number that decides whether it works is the count of freed blocks, not the count of evicted tokens. You can find the NVIDIA write-up here: I wrote a first-principles breakdown of how the KV cache works. It walks through why the model stores keys and values at all, why the cache grows with every token, and a comparison of LLM generation speed with and without KV caching. Read it below.

Avi Chawla

267,009 次观看 • 15 天前

Last week, we launched "Attention in Transformers: Concepts and Code in PyTorch" instructed by Joshua Starmer! In this course, you'll: ✅ Learn how the attention mechanism in LLMs helps convert base token embeddings into rich context-aware embeddings. ✅ Understand the Query, Key, and Value matrices, what they are for, how to produce them, and how to use them in attention. ✅ Learn the difference between self-attention, masked self-attention, and cross-attention, and how multi-head attention scales the algorithm. 🔗 Enroll for free:

Last week, we launched "Attention in Transformers: Concepts and Code in PyTorch" instructed by Joshua Starmer! In this course, you'll: ✅ Learn how the attention mechanism in LLMs helps convert base token embeddings into rich context-aware embeddings. ✅ Understand the Query, Key, and Value matrices, what they are for, how to produce them, and how to use them in attention. ✅ Learn the difference between self-attention, masked self-attention, and cross-attention, and how multi-head attention scales the algorithm. 🔗 Enroll for free:

DeepLearning.AI

36,832 次观看 • 1 年前

$Introducing SubQ - a major breakthrough in LLM intelligence. It is the first model built on a fully sub-quadratic sparse-attention architecture (SSA), And the first frontier model with a 12 million token context window which is: - 52x faster than FlashAttention at 1MM tokens - Less than 5% the cost of Opus Transformer-based LLMs waste compute by processing every possible relationship between words (standard attention). Only a small fraction actually matter. Subquadratic finds and focuses only on the ones that do. That's nearly 1,000x less compute and a new way for LLMs to scale.$

Introducing SubQ - a major breakthrough in LLM intelligence. It is the first model built on a fully sub-quadratic sparse-attention architecture (SSA), And the first frontier model with a 12 million token context window which is: - 52x faster than FlashAttention at 1MM tokens - Less than 5% the cost of Opus Transformer-based LLMs waste compute by processing every possible relationship between words (standard attention). Only a small fraction actually matter. Subquadratic finds and focuses only on the ones that do. That's nearly 1,000x less compute and a new way for LLMs to scale.

Alexander Whedon

13,184,597 次观看 • 2 个月前

SORA by Hand ✍️ OpenAI’s #SORA took over the Internet when it was announced earlier this year. The technology behind Sora is the Diffusion Transformer (DiT) developed by William Peebles and Shining Xie. How does DiT work? 𝗚𝗼𝗮𝗹: Generate a video conditioned by a text prompt and a series of diffusion steps [1] Given ↳ Video ↳ Prompt: "sora is sky" ↳ Diffusion step: t = 3 [2] Video → Patches ↳ Divide all pixels in all frames into 4 spacetime patches [3] Visual Encoder: Pixels 🟨 → Latent 🟩 ↳ Multiply the patches with weights and biases, followed by ReLU ↳ The result is a latent feature vector per patch ↳ The purpose is dimension reduction from 4 (2x2x1) to 2 (2x1). ↳ In the paper, the reduction is 196,608 (256x256x3)→ 4096 (32x32x4) [4] ⬛ Add Noise ↳ Sample a noise according to the diffusion time step t. Typically, the larger the t, the smaller the noise. ↳ Add the Sampled Noise to latent features to obtain Noised Latent. ↳ The goal is to purposely add noise to a video and ask the model to guess what that noise is. ↳ This is analogous to training a language model by purposely deleting a word in a sentence and ask the model to guess what the deleted word was. [5-7] 🟪 Conditioning by Adaptive Layer Norm [5] Encode Conditions ↳ Encode "sora is sky" into a text embedding vector [0,1,-1]. ↳ Encode t = 3 to as a binary vector [1,1]. ↳ Concatenate the two vectors in to a 5D column vector. [6] Estimate Scale/Shift ↳ Multiply the combined vector with weights and biases ↳ The goal is to estimate the scale [2,-1] and shift [-1,5]. ↳ Copy the result to (X) and (+) [7] Apply Scale/Sift ↳ Scale the noised latent by [2,-1] ↳ Shifted the scaled noised latent by [-1, 5] ↳ The result is "conditioned" noise latent. [8-10] Transformer [8] Self-Attention ↳ Feed the conditioned noised latent to Query-Key function to obtain a self-attention matrix ↳ Value is omitted for simplicity [9] Attention Pooling ↳ Multiply the conditioned noised latent with the self-attention matrix ↳ The result are attention weighted features [10] Pointwise Feed Forward Network ↳ Multiply the attention weighted features with weights and biases ↳ The result is the Predicted Noise 🏋️‍♂️ 𝗧𝗿𝗮𝗶𝗻 [11] ↳ Calculate MSE loss gradients by taking the different between the Predicted Noise and the Sampled Noise (ground truth). ↳ Use the loss gradients to kick off backpropagation to update all learnable parameters (red borders) ↳ Note the visual encoder and decoder's parameters are frozen (blue borders) 🎨 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗲 (𝗦𝗮𝗺𝗽𝗹𝗲) [12] Denoise ↳ Subtract the predicted noise from the noised latent to obtain the noise-free latent [13] Visual Decoder: Latent 🟩 → Pixels 🟨 ↳ Multiply the patches with weights and biases, followed by ReLU [14] Patches → Video ↳ Rearrange patches into a sequence of video frames.

SORA by Hand ✍️ OpenAI’s #SORA took over the Internet when it was announced earlier this year. The technology behind Sora is the Diffusion Transformer (DiT) developed by William Peebles and Shining Xie. How does DiT work? 𝗚𝗼𝗮𝗹: Generate a video conditioned by a text prompt and a series of diffusion steps [1] Given ↳ Video ↳ Prompt: "sora is sky" ↳ Diffusion step: t = 3 [2] Video → Patches ↳ Divide all pixels in all frames into 4 spacetime patches [3] Visual Encoder: Pixels 🟨 → Latent 🟩 ↳ Multiply the patches with weights and biases, followed by ReLU ↳ The result is a latent feature vector per patch ↳ The purpose is dimension reduction from 4 (2x2x1) to 2 (2x1). ↳ In the paper, the reduction is 196,608 (256x256x3)→ 4096 (32x32x4) [4] ⬛ Add Noise ↳ Sample a noise according to the diffusion time step t. Typically, the larger the t, the smaller the noise. ↳ Add the Sampled Noise to latent features to obtain Noised Latent. ↳ The goal is to purposely add noise to a video and ask the model to guess what that noise is. ↳ This is analogous to training a language model by purposely deleting a word in a sentence and ask the model to guess what the deleted word was. [5-7] 🟪 Conditioning by Adaptive Layer Norm [5] Encode Conditions ↳ Encode "sora is sky" into a text embedding vector [0,1,-1]. ↳ Encode t = 3 to as a binary vector [1,1]. ↳ Concatenate the two vectors in to a 5D column vector. [6] Estimate Scale/Shift ↳ Multiply the combined vector with weights and biases ↳ The goal is to estimate the scale [2,-1] and shift [-1,5]. ↳ Copy the result to (X) and (+) [7] Apply Scale/Sift ↳ Scale the noised latent by [2,-1] ↳ Shifted the scaled noised latent by [-1, 5] ↳ The result is "conditioned" noise latent. [8-10] Transformer [8] Self-Attention ↳ Feed the conditioned noised latent to Query-Key function to obtain a self-attention matrix ↳ Value is omitted for simplicity [9] Attention Pooling ↳ Multiply the conditioned noised latent with the self-attention matrix ↳ The result are attention weighted features [10] Pointwise Feed Forward Network ↳ Multiply the attention weighted features with weights and biases ↳ The result is the Predicted Noise 🏋️‍♂️ 𝗧𝗿𝗮𝗶𝗻 [11] ↳ Calculate MSE loss gradients by taking the different between the Predicted Noise and the Sampled Noise (ground truth). ↳ Use the loss gradients to kick off backpropagation to update all learnable parameters (red borders) ↳ Note the visual encoder and decoder's parameters are frozen (blue borders) 🎨 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗲 (𝗦𝗮𝗺𝗽𝗹𝗲) [12] Denoise ↳ Subtract the predicted noise from the noised latent to obtain the noise-free latent [13] Visual Decoder: Latent 🟩 → Pixels 🟨 ↳ Multiply the patches with weights and biases, followed by ReLU [14] Patches → Video ↳ Rearrange patches into a sequence of video frames.

Tom Yeh

238,166 次观看 • 2 年前

The next chapter about transformers is up on YouTube, digging into the attention mechanism: The model works with vectors representing tokens (think words), and this is the mechanism that allows those vectors to take in meaning from context.

The next chapter about transformers is up on YouTube, digging into the attention mechanism: The model works with vectors representing tokens (think words), and this is the mechanism that allows those vectors to take in meaning from context.

Grant Sanderson

810,238 次观看 • 2 年前

The inventor of Disagg Prefill, Hao Zhang , drops a new technique called Core Attention Disagg (CAD) which optimizes long context training by disaggregating only the core attention softmax(QK^T)V from the rest of the layers. This is compared to Attention-FFN Disagg (AFD) that attention (including QKV proj & Attention Output Proj) from FFN layers. CAD decouples the layer with quadratic compute growth with respect to seq length from the rest of the layers which only has near linear growth.

The inventor of Disagg Prefill, Hao Zhang , drops a new technique called Core Attention Disagg (CAD) which optimizes long context training by disaggregating only the core attention softmax(QK^T)V from the rest of the layers. This is compared to Attention-FFN Disagg (AFD) that attention (including QKV proj & Attention Output Proj) from FFN layers. CAD decouples the layer with quadratic compute growth with respect to seq length from the rest of the layers which only has near linear growth.

SemiAnalysis

21,896 次观看 • 6 个月前

LangChain's co-founder: "memory can be a real moat." the architecture that builds this? four markdown files and a cron job. someone open sourced the full stack. memory layers, self-rewriting skills, a dream cycle that runs at 3am. yes, you should read every word of this.

LangChain's co-founder: "memory can be a real moat." the architecture that builds this? four markdown files and a cron job. someone open sourced the full stack. memory layers, self-rewriting skills, a dream cycle that runs at 3am. yes, you should read every word of this.

Rohit

219,848 次观看 • 2 个月前

i'm running a 397 billion parameter model on a amd ai max box that sits on my desk and pulls less power than a gaming laptop. the model is Nex-N2-Pro, 397B-A17B, the open weight release people are putting next to gpt-5.5 on coding. i have it quantized to IQ1_M, 1.75 bits per weight, 90gb of weights loaded into the 128gb of unified memory on amd's strix halo igpu. watch the gpu in this recording. it spikes, it sustains, it does not fall over. that is the part the spec sheets never show you, not just that a 400b model loads, but that an integrated graphics chip holds the load and generates token after token, stable, no crash, no thermal cliff. and it is not a slideshow. roughly 18 tokens a second, faster than you can read. a frontier scale model producing usable output, fully local. no datacenter, no rented h100s, no api key, no permission. three years ago a model this size meant a server room and a budget to match. tonight it is a quiet box on my desk. this is the accessible tier almost nobody benchmarks honestly, and it is further along than the timeline thinks. the full breakdown is coming, rocm vs vulkan on this chip, and this little amd box head to head against the nvidia equivalent. stay tuned.

i'm running a 397 billion parameter model on a amd ai max box that sits on my desk and pulls less power than a gaming laptop. the model is Nex-N2-Pro, 397B-A17B, the open weight release people are putting next to gpt-5.5 on coding. i have it quantized to IQ1_M, 1.75 bits per weight, 90gb of weights loaded into the 128gb of unified memory on amd's strix halo igpu. watch the gpu in this recording. it spikes, it sustains, it does not fall over. that is the part the spec sheets never show you, not just that a 400b model loads, but that an integrated graphics chip holds the load and generates token after token, stable, no crash, no thermal cliff. and it is not a slideshow. roughly 18 tokens a second, faster than you can read. a frontier scale model producing usable output, fully local. no datacenter, no rented h100s, no api key, no permission. three years ago a model this size meant a server room and a budget to match. tonight it is a quiet box on my desk. this is the accessible tier almost nobody benchmarks honestly, and it is further along than the timeline thinks. the full breakdown is coming, rocm vs vulkan on this chip, and this little amd box head to head against the nvidia equivalent. stay tuned.

Sudo su

32,019 次观看 • 27 天前

**Attention Investors** Build any financial model you want in minutes and verify every number with a single click. The Fiscal AI Codex Plugin is insanely powerful.

Attention Investors Build any financial model you want in minutes and verify every number with a single click. The Fiscal AI Codex Plugin is insanely powerful.

Fiscal.ai

27,558 次观看 • 1 个月前

🇺🇸 Chamath just revealed the truth on Rogan… attention is what runs it all. Google ranks the web by attention. Facebook and Instagram are built to capture attention. The most important AI paper ever written is literally called "Attention Is All You Need." Every system that now runs the world reduces to the same single currency. And at some point, that stops sounding like branding and starts sounding like a warning. Joe Rogan, Chamath Palihapitiya

🇺🇸 Chamath just revealed the truth on Rogan… attention is what runs it all. Google ranks the web by attention. Facebook and Instagram are built to capture attention. The most important AI paper ever written is literally called "Attention Is All You Need." Every system that now runs the world reduces to the same single currency. And at some point, that stops sounding like branding and starts sounding like a warning. Joe Rogan, Chamath Palihapitiya

Mario Nawfal

314,714 次观看 • 2 个月前

Satya Nadella reveals why every company may need its own AI model: the model becomes the new company database. "To me, a model is like the database market." "A firm should be able to take the tacit knowledge it has and embed it inside weights in a model that they control." "When somebody asks me how many models should there be, I'll say as many models as firms in the world." The contrarian part: the value may not sit in one universal frontier model. It sits in each company turning its private operating knowledge into a controlled model.

Satya Nadella reveals why every company may need its own AI model: the model becomes the new company database. "To me, a model is like the database market." "A firm should be able to take the tacit knowledge it has and embed it inside weights in a model that they control." "When somebody asks me how many models should there be, I'll say as many models as firms in the world." The contrarian part: the value may not sit in one universal frontier model. It sits in each company turning its private operating knowledge into a controlled model.

Karl Mehta

465,887 次观看 • 19 天前

Parasites paralyze the snail and attract attention so that it is eaten by a bird. The parasite uses the bird as a host to grow in its digestive tract

Parasites paralyze the snail and attract attention so that it is eaten by a bird. The parasite uses the bird as a host to grow in its digestive tract

Nature is Amazing ☘️

2,454,380 次观看 • 1 年前

You may change your mental vibrations by an effort of WILL in the direction of deliberately fixing the Attention upon a more desirable state. Will directs the ATTENTION, and Attention changes the Vibration. Cultivate the Art of Attention by means of the Will, and you have solved the secret of the MASTERY of Moods and Mental States ~ Kybalion

You may change your mental vibrations by an effort of WILL in the direction of deliberately fixing the Attention upon a more desirable state. Will directs the ATTENTION, and Attention changes the Vibration. Cultivate the Art of Attention by means of the Will, and you have solved the secret of the MASTERY of Moods and Mental States ~ Kybalion

WhatdoIknow

17,192 次观看 • 10 个月前

"Why do you need a token?" Rob Hadick ＞|＜ says to R𝕚𝕔𝕙𝕒𝕣𝕕⚡︎𝕠𝕟 2084 that should be the first question every application founder asks. Before launching a token, ask yourself: What value does it create, and who captures that value?

"Why do you need a token?" Rob Hadick ＞|＜ says to R𝕚𝕔𝕙𝕒𝕣𝕕⚡︎𝕠𝕟 2084 that should be the first question every application founder asks. Before launching a token, ask yourself: What value does it create, and who captures that value?

Bitcoin.com News

26,690 次观看 • 19 天前

What is Proof of attention, by @_kaitoai ? Yu Hu 🌊 explains that proof of attention is the top 1000 yappers’ yaps that are now accessible on chain and that can be used by anyone to create anything based on the Yappers’ social scores Some projects like Quai Network ⚡️💵 and Berachain Foundation 🐻⛓ are already leveraging Proof of Attention to improve their token and NFT GTM strategy And this is just the start👇🏻

What is Proof of attention, by @_kaitoai ? Yu Hu 🌊 explains that proof of attention is the top 1000 yappers’ yaps that are now accessible on chain and that can be used by anyone to create anything based on the Yappers’ social scores Some projects like Quai Network ⚡️💵 and Berachain Foundation 🐻⛓ are already leveraging Proof of Attention to improve their token and NFT GTM strategy And this is just the start👇🏻

MR SHIFT 🦁

15,810 次观看 • 1 年前

New short course on advanced retrieval for RAG (retrieval augmented generation)! RAG fetches relevant documents to give context to an LLM. In Advanced Retrieval for AI with Chroma, taught by Chroma founder anton 🇺🇸, you’ll learn: (i) Query expansion using an LLM to rewrite and improve a query, by either generating either additional relevant queries or a hypothetical answer to the query. (ii) Reranking using a cross-encoder - a model trained to measure similarity between two inputs presented simultaneously. Reranking reorders retrieved documents based on the cross-encoder similarity measure. (iii) Constructing and training an Embedding Adaptor, which is a model that adapts the embedding values to be more relevant to your use case. Each of these techniques can help you build much better RAG systems. Please sign up for the course here:

New short course on advanced retrieval for RAG (retrieval augmented generation)! RAG fetches relevant documents to give context to an LLM. In Advanced Retrieval for AI with Chroma, taught by Chroma founder anton 🇺🇸, you’ll learn: (i) Query expansion using an LLM to rewrite and improve a query, by either generating either additional relevant queries or a hypothetical answer to the query. (ii) Reranking using a cross-encoder - a model trained to measure similarity between two inputs presented simultaneously. Reranking reorders retrieved documents based on the cross-encoder similarity measure. (iii) Constructing and training an Embedding Adaptor, which is a model that adapts the embedding values to be more relevant to your use case. Each of these techniques can help you build much better RAG systems. Please sign up for the course here:

Andrew Ng

191,219 次观看 • 2 年前