COMMITS
/ examples/multi_agent/agent_system.py June 21, 2026
Z
Extract append_response_tokens to Sample (#2108)
Zilin Zhu committed
June 4, 2026
Z
Revert "rename rollout_ids to group_ids" (#2013)
Zilin Zhu committed
June 1, 2026
J
fix(multi-agent): preserve rollout logprobs (#1995)
Jiang1216 committed
May 30, 2026
Z
rename rollout_ids to group_ids (#1984)
Zilin Zhu committed
May 25, 2026
Z
[2/N] Support training with variable global batch size (#1933)
Zilin Zhu committed
March 22, 2026
H
chore: translate remaining Chinese comments to English (#1726)
Hubert Wang committed
January 8, 2026
M
update code (#1358)
miles-code-angel committed
赵
Revert "code sync" (#1357)
赵晨阳 committed
M
code sync (#1356)
miles-code-angel committed
December 16, 2025
N
fix: improve tokenization (#1113)
Nan Jiang committed
December 1, 2025
F
[4/N] Tiny enable `UP` ruleset in Ruff (#994)
fzyzcjy committed
F
[3/N] Enable `B` ruleset in Ruff (#993)
fzyzcjy committed
September 15, 2025
Z
[feat] use one global httpx.AsyncClient and remove --use-http2 (#338)
Zilin Zhu committed
September 5, 2025
Z
[refactor] Add isort back and move global gloo to global util (#273)
Zilin Zhu committed
September 4, 2025
Y
[feature] add an multi-agent RL example (#269)
Yinpei Su committed