陶智勇@tri_dao
· 2026-09-01 11:58
陶智勇
@tri_dao · Tri Dao · 0 followers
将有更多 GPU 算力用于开源模型。
2今日信号
今日没有多源共振的事件
📘 开源 vs 闭源战局
1 条最高 7.6
📘 AI 硬件
1 条最高 6.4
陶智勇@tri_dao
· 2026-08-19 01:01
这些人行动真快，第一个机柜已经发货了。更多的推理算力总是受欢迎的。
言外之意，
事实Flash Attention 作者确认新型推理硬件首批机柜已完成交付发货。
观点这表明专用/新型推理算力正在加速进入实际部署阶段。
对你意味着，基础设施层推理算力供给增多将逐步缓解算力瓶颈并推低推理成本，建议在规划长期 Agent 与高频调用产品架构时，提前制定更具性价比的算力采购与调度策略。
These guys move fast, 1st rack already ships. More inference compute is always welcome
尚未被主编选入事件/主题的原始推文（共 50 条，按时间倒序）
陶智勇 @tri_dao08-13 07:06
I really like this new benchmark. Has the flavor of ARC-AGI3 but it’s pure text so you don’t have to worry about the vision capability
🔗 原推陶智勇 @tri_dao07-29 05:42
RT Nadav Timor: the gains come entirely from wrapping π0.5 in an agent that plans, verifies, and recovers. no new finetuning. @lianegalanti and team ...
🔗 原推陶智勇 @tri_dao07-29 02:46
Putting LLM brain on robots -> 4x SOTA with no extra training. I’ve been very surprised by how well this works. The time for agents running on robots...
🔗 原推陶智勇 @tri_dao07-28 02:08
RT Together AI: Kimi K3 is now live on Together AI. We’re proud to be a Day 0 launch partner for @Kimi_Moonshot’s open frontier model, built for lon...
🔗 原推陶智勇 @tri_dao07-08 15:22
RT Together AI: We're introducing Provisioned Throughput: reserved inference capacity for frontier open models, with token-based pricing and a 99% upt...
🔗 原推陶智勇 @tri_dao07-02 05:17
We’re serving 400T tokens / month and the demand for open models just keep going up
🔗 原推陶智勇 @tri_dao07-01 22:07
RT Vipul Ved Prakash: We @togethercompute believe intelligence should be abundant, not expensive. Today we announced our Series C funding of $800m @ $...
🔗 原推陶智勇 @tri_dao06-30 23:31
If you ever wondered about how how open/closed model makers and inference providers make economic sense, this is the piece to read
🔗 原推陶智勇 @tri_dao06-30 23:10
It's wild how quickly Etched designed and got the chips out, all within 2 years. They went deep, hardcoding attention into silicon and getting very hi...
🔗 原推陶智勇 @tri_dao06-25 23:19
RT Neil Movva: Samir Menon @blintzbase and I are thrilled to announce Sail @sailresearchco ! We build infrastructure for long-horizon agents: inferenc...
🔗 原推陶智勇 @tri_dao06-16 05:05
RT Together AI: Cartesia Sonic 3.5 is now available on Together AI. We added 150+ @cartesia Sonic 3.5 voices to voice finder, so developers can listen...
🔗 原推陶智勇 @tri_dao06-16 01:34
RT Albert Gu: Within the span of a week, we launched streaming TTS (text-to-speech) and STT (speech-to-text) models that topped the leaderboards. I'm ...
🔗 原推陶智勇 @tri_dao06-16 00:31
RT Karan Goel: We released Sonic-3.5 and Ink-2, the #1 streaming models for text to speech and speech to text you can use in your voice agents today. ...
🔗 原推陶智勇 @tri_dao06-15 21:49
As hybrid models (Qwen 3.5 / Nemotron Ultra) run agents with massive context, Gated-DeltaNet / Mamba states become a bottleneck. A simple insight to m...
🔗 原推陶智勇 @tri_dao06-15 20:21
RT Eric Nguyen: Together with my co-founders Michael @MichaelPoli6, Stefano @Massastrello and Armin @athmsx, I am excited to announce @RadicalNumerics...
🔗 原推陶智勇 @tri_dao06-14 07:06
RT Together AI: Kimi-K2.7-Code from @Kimi_Moonshot is now available on Together AI. Built on Kimi K2.6, it’s a coding-focused agentic model for long-...
🔗 原推陶智勇 @tri_dao05-29 08:41
RT Mark Saroufim: My MLSys keynote on AI writing systems code got more interest than I expected. The recording will take a while, so in the finest tra...
🔗 原推陶智勇 @tri_dao05-29 01:26
RT Albert Gu: Our new model Ink-2 tops AA's leaderboard for streaming speech-to-text! Ink-2 comes with plenty of features optimized for real-time voic...
🔗 原推陶智勇 @tri_dao05-29 00:50
RT Cartesia: Cartesia Ink-2 debuts as #1 for accuracy on the brand-new streaming speech-to-text leaderboard from @ArtificialAnlys! We designed Ink-2 f...
🔗 原推陶智勇 @tri_dao05-28 00:56
RT LightSeek Foundation: Proud to collaborate with the @Alibaba_Qwen, @NVIDIAAI, @KVCache_AI, @PyTorch, and FlashAttention @tri_dao on this effort �...
🔗 原推陶智勇 @tri_dao05-28 00:02
RT PyTorch: The speed-of-light optimization for Qwen3.5 on the TokenSpeed inference engine is a significant milestone, achieving a record-breaking 580...
🔗 原推陶智勇 @tri_dao05-23 02:30
RT Clive Chan: the transformer reparameterizations lab has released even more reparameterizations :D
🔗 原推陶智勇 @tri_dao05-22 09:51
After some mathematical rewrite, turns out all of transformer is a series of gemm + epilogue. Given a few optimized primitives, LLMs (and novice human...
🔗 原推陶智勇 @tri_dao05-22 09:16
RT Together AI: Introducing Qwen3.7-Max from @Alibaba_Qwen, Qwen’s flagship model for the agent era with 1M context and leading performance across ag...
🔗 原推陶智勇 @tri_dao05-22 08:39
RT Oliver Sieberling: A significant portion of transformer training time is not spend doing matmuls, but for norms, residuals, RoPE, etc. This work sh...
🔗 原推陶智勇 @tri_dao05-22 07:36
RT Jack Zhang: We built a kernel abstraction to rewrite the entire transformer stack as GEMM + Epilogue kernels! Neural net architectures such as tran...
🔗 原推陶智勇 @tri_dao05-19 02:50
RT Eric Chen: The 100 in A100 is the number of hours you'll spend reading this post. 29,000 words on FlashAttention-2 in CuTe -- a line-by-line dredge...
🔗 原推陶智勇 @tri_dao05-15 02:34
RT Together AI: Seven papers. One research team. Together AI is heading to #MLSys2026 next week. Check out the work going from research to production ...
🔗 原推陶智勇 @tri_dao05-12 08:37
RT Neil Movva: Throughput vs. latency is a foundational tradeoff in almost any system. @sailresearchco is building inference for long-horizon agents, ...
🔗 原推陶智勇 @tri_dao05-07 03:24
RT Flapping Airplanes: (1/5) Great to be at @sequoia to give a sneak peek of one of our research directions! TL;DR one path to data-efficiency may be ...
🔗 原推陶智勇 @tri_dao05-07 00:38
RT Together AI: Together AI has long been a proud supporter of open-source innovation in inference. We're excited for the new TokenSpeed inference eng...
🔗 原推陶智勇 @tri_dao05-06 23:29
RT LightSeek Foundation: Introducing TokenSpeed, a speed-of-light LLM inference engine. > TensorRT LLM level performance > vLLM level usability > Buil...
🔗 原推陶智勇 @tri_dao05-04 06:17
RT driss guessous: I alluded to this a few tweets ago but just pushed up a shortish blog on a subtle feature of CLC work stealing that makes cuda-grap...
🔗 原推陶智勇 @tri_dao05-01 03:54
RT Together AI: Join us Tue 5/5: #DeepSeek-V4's hybrid attention + sparse MoE reduces KV cache up to 90%, enabling 1M-token context. We'll cover why t...
🔗 原推陶智勇 @tri_dao04-24 16:53
RT Ilyas: And we integrated it in Transformers ! As of https://github.com/huggingface/transformers/pull/45433
🔗 原推陶智勇 @tri_dao04-23 07:01
RT Together AI: Introducing Kimi K2.6 from @Kimi_Moonshot, a multimodal agentic model with Agent Swarm scaling to 300 sub-agents and long-horizon codi...
🔗 原推陶智勇 @tri_dao04-23 02:25
RT Mayank Mishra: I love this figure! SonicMoE saves more than 2x memory for Qwen3-235B-A22B 🚀 Check out the full blog: https://dao-lab.ai/blog/202...
🔗 原推陶智勇 @tri_dao04-22 10:57
RT Aran Komatsuzaki: Together AI presents SAW-INT4 Achieves near-BF16 accuracy while preserving the end-to-end performance benefits of INT4
🔗 原推陶智勇 @tri_dao04-17 02:18
The dynamical system view gives very clean conditions for looped transformer to be stable
🔗 原推陶智勇 @tri_dao04-16 00:56
RT Dan Fu: 📢 Super excited to announce Parcae! We've been thinking about scaling laws and the "right" way to get more FLOPs. Turns out layer loopin...
🔗 原推陶智勇 @tri_dao04-14 05:26
RT Together AI: EinsteinArena is a platform where AI agents collaborate on open science problems — submitting solutions, posting in discussion thread...
🔗 原推陶智勇 @tri_dao04-12 09:29
RT Together AI: MiniMax M2.7 is now on Together AI. Trained by letting it run its own RL loop, resulting in the highest open-source score on MLE Bench...
🔗 原推陶智勇 @tri_dao04-11 05:52
RT Monishwaran Maheswaran: Super excited to Introduce our latest work: Squeeze Evolve. We unify test-time scaling methods into one evolutionary framew...
🔗 原推陶智勇 @tri_dao04-08 00:32
RT Hao Kang: Just found out that flashattention use look up table+linear approximation to accelerate softmax. We have tried similar strategies on work...
🔗 原推陶智勇 @tri_dao04-07 00:28
Fast muon optimizer coming to consumer cards. All the code was written as matmul + epilogue so once the mainloop was implemented for Blackwell consume...
🔗 原推陶智勇 @tri_dao04-04 00:52
RT Princeton PLI: Check out latest blog post: Mamba-3: Improved Sequence Modeling using State Space Principles https://pli.princeton.edu/blog/2026/mam...
🔗 原推
生成于 2026-09-25 22:18（北京时间）· v0.2 CEO 战略情报版