Joe Isaacson
@Jisaacso
Followers
471
Following
2K
Media
16
Statuses
188
@ NeurIPS torching pys @pytorch
Seattle, WA
Joined July 2012
Would you rather have better documentation for PyTorch prototype features but more BC breakages or secret APIs until we have more confidence?
2
1
3
🚀🚀🚀 come work with PyTorch on GPU kernel optimization, distributed training/inference/post-training, compiler design, ABI stability
If you’re excited about optimizing code that runs equally well on a single or thousands of GPUs and if you have the ability to submit a single substantial PR to a major OSS library, we want you on the PyTorch team - especially if you’re early in your career.
0
0
2
Excited to share the GPU MODE kernel authoring competition! We’re stoked to see the creative solutions people come up with to push bounds of performance. And, all for a good cause — towards a public dataset of performant kernels 😁
Write a fast kernel and run it on Discord. See how you compare against the best! If you're familiar with Leetcode, Kaggle or Codeforces then this should feel right at home
0
2
14
David Harmeyer on Facebook’s history of Hacker Cup. How to add N flights to N airports to minimize travel distance.
0
2
10
Stoked for the Hacker AI Cup Workshop to start at @NeurIPSConf ! Speakers @weiwei_msr @syhw @WuNeal @simran_s_arora @MishaLaskin @thomascapellajp @marksaroufim ! Come join, room 210
1
2
10
Congrats on the launch of 🌽 KernelBench! We're excited to partner with 🍿 Popcorn to lower the barrier to GPU programming!
We are not the only ones thinking about this direction. The vision was nicely outlined by @karpathy in his talk (see picture below, credit to karpathy and @accel), and we found many others also eager to attempt this. Project 🍿: https://t.co/beW14mg8Pz in the GPU Mode server is
1
2
10
We ran a lot of evals recently using Mistral Large 2 for the hacker cup challenges, Weave’s native integration with the Mistral SDk was super useful to understand token usage and latency, as well as measure accuracy
🚀 Just launched: a guide to observability with @MistralAI! 🔍 Why observability? For visibility, production requirements, reproducibility, & continuous improvement in LLM systems. 😎Monitor input prompts, models, & outputs at the individual level. Track workflow patterns,
0
2
5
PyTorch has historically been super slow for a lot of "small" RL workloads, but the reason is kinda dumb. RL often uses tiny neural networks, and end up ridiculously CPU overhead bound. Luckily, with cudagraphs and torch.compile, we often see >5x speedups! I remember the first
Today we're opensourcing a LeanRL, a simple RL library that provides recipes for fast RL training using torch.compile and cudagraphs. Using these, we get >6x speed-ups compared to the original CleanRL implementations. https://t.co/jKD8cMTFCA A thread ⬇️
7
52
471
A huge thanks to @caseyaylward and the @Accel team for running the highest quality sys ml hackathon I’ve ever see . It was great to meet so many GPU MODE friends IRL, and hack on torchao. And Congrats to the winners for fast flexible attention!
14/ We had so much fun bringing this special community together IRL for an amazing day of technical talks/hacking. Big thanks to everyone who turned out and our planning committee (here’s an “after” photo taken at midnight). Full videos of the talks to follow soon #cudamodeirl.
0
0
5
From the beginning, @neurosp1ke and I wanted a community that was cozy, inclusive and fun where you could make friends and learn how to make your code faster Anyone who shares our ideals is welcome. We’re announcing we’re changing the name of our community to “GPU MODE”.
5
10
117
Excited for our release of LeanRL, showcasing the simplicity and performance of torch compile across a breath of RL Models. Big shout out to @vwxyzjn for the inspiration and support
Today we're opensourcing a LeanRL, a simple RL library that provides recipes for fast RL training using torch.compile and cudagraphs. Using these, we get >6x speed-ups compared to the original CleanRL implementations. https://t.co/jKD8cMTFCA A thread ⬇️
0
2
7
Registration is open for the #NeurIPS2024 HackerCup, the world's first AI programming competition by Microsoft Research, Meta, and PyTorch. Test your AI on the programming problems that challenge the best human minds and see how your AI ranks. Learn more.
hackercupai.github.io
NeurIPS 2024 Challenge
3
28
81
We recently enabled quantization-aware training in torchtune using torchao. QAT helps recover any quality degradation resulting from quantizing the model - especially useful when you’re resource constrained at inference time. 👇🏽awesome work by Andrew Or! https://t.co/53I7qgVcNB
0
6
12
I'm beyond stoked to be hosting the first IRL hackathon for the CUDA MODE community with @Accel @nvidia and @PyTorch ! Get ready to hack across a range of AI performance -- inference optimization, custom kernels, low bit dtypes, sparsification, ...
This September, we’re hosting a CUDA MODE hackathon alongside our friends at @nvidia and @PyTorch. Join us in San Francisco to spend the day hacking on new projects and hear from some of the most well-respected ML leaders at @Meta/@PyTorch, @EurekaLabsAI, @vllm_project,
0
2
6
Check out the first AI track of the Meta Hacker Cup ! 5 rounds, some of the hardest problems in code generation, same problems released to human and AI competitors this year. Large Discord group with competitors, just getting started https://t.co/7Gclo7a4C2
Timeline for AI to achieve IOI (not IMO) gold
0
1
4
We've kicked off the NeurIPS Meta Hacker Cup AI track! I mostly use LLMs to code and they've been great at removing the drudgery of boiler-platy code but for harder problems they are meh Both the big-boi llamas and GPT-4 fall flat on their face!
1
7
49