Francisco Massa
@fvsmassa
Research Engineer at Facebook AI Research working on PyTorch.
ID:832596127962775552
17-02-2017 14:22:40
314 Tweets
3,4K Followers
11 Following
Announcing Flash-Decoding, to make long-context LLM inference up to 8x faster! Great collab with Daniel Haziza, Francisco Massa and Grigory Sizov.
Main idea: load the KV cache in parallel as fast as possible, then separately rescale to combine the results.
1/7
We just introduced PyTorch 2.0 at the #PyTorchConference , introducing torch.compile!
Available in the nightlies today, stable release Early March 2023.
Read the full post: bit.ly/3VNysOA
🧵below!
1/5
Glad to present our work with Francisco Massa and Alexandre Défossez « Hybrid Transformers for Music Source Separation » done at @MetaAI.
We achieve 9.20 dB of SDR on the MUSDB18 test set.
- paper: arxiv.org/abs/2211.08553
- code: github.com/facebookresear…
- audio: ai.honu.io/papers/htdemuc…
1/5
[🧠👨💻 ML Coding Series] Continuing on with the ML coding series! This might be the most thorough ML paper explanation in history - 1h and 45 minutes! 😅
Facebook (now @MetaAI) DETR explained
YT: youtu.be/xkuoZ50gK4Q
Nicolas Carion Francisco Massa Gabriel Synnaeve Alexander Kirillov Sergey Zagoruyko
1/
The latest release of TorchVision has a feature extraction utility. Super handy - check it out. Thanks Francisco Massa and team for helping put this together.
Looking forward to using this new functionality to allow more flexible feature extraction in timm -- especially for vision transformers and mlp models. Thanks Alexander Soare and Francisco Massa