FP8-RL: A Practical and Stable Low-Precision Stack for LLM Reinforcement Learning
Paper
•
2601.18150
•
Published
•
6
Lark Zhang
larkZ
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
7 days ago
FP8-RL: A Practical and Stable Low-Precision Stack for LLM Reinforcement Learning
updated
a model
about 2 months ago
pe-nlp/Qwen3-8B-Base-scaled
published
a model
about 2 months ago
pe-nlp/Qwen3-8B-Base-scaled
Organizations
upvoted
a
paper
7 days ago