F-G Fernandez

@FrG_FM

Deep Learning Engineer by day, OSS contributor by night 🦇 | building @rimward_ai @pyro_near | prev @ycombinator (YC S23) @CentraleSupelec

San Francisco, CA

Joined October 2013

Pinned
F-G Fernandez
@FrG_FM
Jun 2, 2023
Last Friday, we were invited to join the roundtable discussion with @sama, CEO @OpenAI & former president of YC. A humbling experience & fitting coincidence, since @quack_ai has been selected to join the prestigious batch of @ycombinator 🚀 Credits: Romain Ruiz 📸
F-G Fernandez
@FrG_FM
Feb 6, 2025
This attention to design deserves all the praise. Now, I need to resist the urge to spend my weekend learning animation design 🙈
Jibraan
@KadriJibraan
Feb 5, 2025
make software silly again
00:00
F-G Fernandez
@FrG_FM
Sep 24, 2024
Hello SF 🇺🇸 I’m in town for the next 2 weeks: who should I meet? Looking for hacking sessions & interesting chats with tech people. I’ll be at the #DPESummit this week and the @ycombinator reunion next week!
F-G Fernandez
@FrG_FM
Jul 11, 2024
The moment when FlashAttention starts to challenge @nvidia cuDNN on benchmarks👀 This is such an interesting space of research, and it doesn't get enough credits. Kudos to entire team ⚡️
Tri Dao
@tri_dao
Jul 11, 2024
FlashAttention is widely used to accelerate Transformers, already making attention 4-8x faster, but has yet to take advantage of modern GPUs. We’re releasing FlashAttention-3: 1.5-2x faster on FP16, up to 740 TFLOPS on H100 (75% util), and FP8 gets close to 1.2 PFLOPS! 1/
F-G Fernandez
@FrG_FM
Jun 20, 2024
The history of @Docker laid bare before our eyes by @justincormack 🐳 Best meme game at #AIDev so far