Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow
Paper
•
2601.14243
•
Published
•
8
Neil
NneilNight
AI & ML interests
AI & ML
Recent Activity
upvoted
a
paper
about 6 hours ago
Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow
new activity
about 2 months ago
xihc-ucb/Qwen2.5-7B-Instruct-train-Quasar-1002:Upload FP8Qwen2ForCausalLM
new activity
2 months ago
xihc-ucb/Qwen2.5-7B-train-Quasar-1002:Upload FP8Qwen2ForCausalLM
Organizations
None yet
upvoted
a
paper
about 6 hours ago
Upload FP8Qwen2ForCausalLM
#7 opened about 2 months ago
by
NneilNight
Upload FP8Qwen2ForCausalLM
#6 opened 2 months ago
by
NneilNight
Upload FP8Qwen2ForCausalLM
#6 opened 2 months ago
by
NneilNight
force push
#5 opened 2 months ago
by
NneilNight
force push
#5 opened 2 months ago
by
NneilNight
force push
#4 opened 2 months ago
by
NneilNight
force push
#4 opened 2 months ago
by
NneilNight
force push
#3 opened 2 months ago
by
NneilNight
force push
#3 opened 2 months ago
by
NneilNight
Upload FP8Qwen2ForCausalLM
#2 opened 2 months ago
by
NneilNight
Upload FP8Qwen2ForCausalLM
#2 opened 2 months ago
by
NneilNight
Upload FP8Qwen2ForCausalLM
#1 opened 2 months ago
by
NneilNight
Upload FP8Qwen2ForCausalLM
#1 opened 2 months ago
by
NneilNight
upvoted
a
paper
4 months ago
upvoted
a
paper
8 months ago
published
a
model
11 months ago