Loreon
Labs
Platform
Docs
Home
Ecosystems
Other
RL
Scalable toolkit for efficient model reinforcement
Other
Emerging
GitHub
Website
Stars
—
Forks
—
Contributors
8
Last push
6mo ago
Recent commits
Latest commits.
feat: add dapo recipe and test (#1617)
56e8fcb
Zhiyu Li
6mo ago
fix: Fix crash when using activation_checkpointing (#1676)
02d5142
Yi-Fu Wu
6mo ago
fix: Fix fp8 after vllm v0.11.2 bump (#1660)
b238e41
Guyue Huang
6mo ago
test: Perf recipe for v0.5 (#1667)
fab6234
Guyue Huang
6mo ago
fix: Fix Fp8 sequence padding for PP>1 case (#1579)
d0651dd
Guyue Huang
6mo ago
fix: Fix crash when using cp in dtensor path (#1663)
91658c8
Yi-Fu Wu
6mo ago
fix: Handle disabled validation in SFT training (#1611)
4794ca7
sahgerlad
6mo ago
fix: Support datasets saved with save_to_disk in ResponseDataset (#1610)
48dbb37
sahgerlad
6mo ago
Top contributors
Builders behind this project.
terrykong
144 commits
ashors1
60 commits
parthchadha
58 commits
chtruong814
48 commits
yuki-97
48 commits
SahilJain314
39 commits
yfw
35 commits
youngeunkwon0405
19 commits