AlphaUncommon
yaof20/Flash-RL
Implementation for FP8/INT8 Rollout for RL training without performence drop.
- Owner
- yaof20 (personal account)
- Stars
- Stars: 309
- Forks
- Forks: 23
- Language
- Python
- License
- MIT
- Created
- 2025
- Topics
- reinforcement-learningvllm
- Tier
- Alpha (250 to 699 ★) What this tier means
Nearby in Python
All Python repos- YutoTerashima/agent-safety-eval-labStars: 309PythonAlpha
- akihitohyh/chatgpt-register-sub2apiStars: 309PythonAlpha
- MobiusQuant/Gendangzou-skillStars: 309PythonAlpha
- JosephSalisbury/python-bittorrentStars: 309PythonAlpha
- jmoiron/johnny-cacheStars: 309PythonAlpha
- raymontag/keepasscStars: 309PythonAlpha