Christopher De Sa

26 posts

Christopher De Sa

Christopher De Sa

@chrismdesa

Katılım Mayıs 2017
23 Takip Edilen502 Takipçiler
Christopher De Sa retweetledi
Tianqi Chen
Tianqi Chen@tqchenml·
Learn more about the latest advances in AI and systems, including LLM serving, efficient attentions, structured outputs, scaling up training, and more topics. Check out #MLSys2025. Accepted papers at mlsys.org/virtual/2025/p… and register today at mlsys.org/Register
Tianqi Chen tweet media
English
4
24
102
16.8K
Christopher De Sa retweetledi
Albert Tseng
Albert Tseng@tsengalb99·
🦙QTIP 2, 3 and 4 bit Llama 3.3 models are now up on HF: huggingface.co/collections/re…. Almost no zeroshot degradation at all sizes. 2 bit QTIP 3.3 70B fits on a single 4090 and gives pretty high quality generations (📹).
Albert Tseng tweet media
English
1
4
7
953
Christopher De Sa retweetledi
Albert Tseng
Albert Tseng@tsengalb99·
🧵 🏎️ Want faster, better quantized LLMs? Introducing QTIP, a new LLM quantization method that achieves a SOTA combination of quality and speed – outperforming methods like QuIP#! 🧑‍💻+🦙(w/ 2 bit 405B!): github.com/Cornell-RelaxM… 📜arxiv.org/abs/2406.11235
Albert Tseng tweet media
English
4
21
76
14K
Christopher De Sa retweetledi
SambaNova
SambaNova@SambaNovaAI·
🚀🌟🚀Excited to announce Samba-CoE v0.2, which outperforms DBRX by @DbrxMosaicAI and @databricks, Mixtral-8x7B from @MistralAI, and Grok-1 by @grok at a breakneck speed of 330 tokens/s. These breakthrough speeds were achieved without sacrificing precision and only on 8 sockets, showcasing the true capabilities of dataflow! Why would you buy 576 sockets and go to 8 bits when you can run using 16 bits and just 8 sockets. Try out the model and check out the speed here - coe-1.cloud.snova.ai. We are also providing a sneak peak of our next model, Samba-CoE v0.3, available soon with our partners at @LeptonAI. Read more about this announcement at sambanova.ai/blog/accurate-…
SambaNova tweet media
English
23
94
369
1.2M
Christopher De Sa
Christopher De Sa@chrismdesa·
New this year, there will be a Young Professionals Symposium on Monday, which provides a forum for young professionals in industry and academia, to discuss important research & career questions/challenges: abstract submissions are now open (sites.google.com/view/mlsys24yps).
English
0
0
1
372
Christopher De Sa
Christopher De Sa@chrismdesa·
This year’s conference will be held at the Santa Clara Convention Center, from Mon May 13th through Thu the 16th, and features keynote speakers: Yejin Choi (University of Washington/Allen Institute for AI), Jeff Dean (Google), and Zico Kolter (CMU/Bosch Center for AI).
English
1
0
0
729
Christopher De Sa retweetledi
Albert Tseng
Albert Tseng@tsengalb99·
🧵 (1/n) 👉 Introducing QuIP#, a new SOTA LLM quantization method that uses incoherence processing from QuIP & lattices to achieve 2 bit LLMs with near-fp16 performance! Now you can run LLaMA 2 70B on a 24G GPU w/out offloading! 💻 cornell-relaxml.github.io/quip-sharp/
Albert Tseng tweet mediaAlbert Tseng tweet media
English
25
197
1K
363.3K
Christopher De Sa retweetledi
Malcolm Harris
Malcolm Harris@BigMeanInternet·
Schools are shutting down today, but childcare is still a collective social responsibility. I've spent the last few days working with a crack team of coders to build this (incredibly cool) tool for scheduling MICRO childcare co-ops childcarecoop.org
Malcolm Harris tweet media
English
23
387
937
0