Skip to content

Pull requests: THUDM/slime

New pull request New
98 Open 1,259 Closed
98 Open 1,259 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Support qwen3.5 loss mask for multi-turn SFT
#1742 opened Mar 19, 2026 by huang3eng Loading…
2
(fix):not have encoder_only attr cause run failed
#1741 opened Mar 19, 2026 by wangyufak Loading…
fix: propagate moe_token_dispatcher_type in bridge model provider
#1737 opened Mar 18, 2026 by nanjiangwill Loading…
1
fix: resolve rope_theta from rope_parameters in DeepseekV32Bridge
#1734 opened Mar 17, 2026 by stevewx Loading…
3 tasks done
[docker] fix qwen3_vl visual module loading
#1727 opened Mar 15, 2026 by ZHZisZZ Loading…
1
chore: translate remaining Chinese comments to English
#1726 opened Mar 15, 2026 by WangHong-yang Loading…
feat: add Qwen3.5-4B model support
#1721 opened Mar 13, 2026 by shihaohou Loading…
small fix on qwen3-235b-a22b launch script
#1719 opened Mar 12, 2026 by Zhuohao-Li Loading…
fix: http_utils. disable system proxy for internal SGLang httpx clients
#1714 opened Mar 12, 2026 by DongzhuoranZhou Loading…
Add Mooncake Backend for Rollout Data Transfer run-ci-megatron
#1709 opened Mar 11, 2026 by zxpdemonio Loading…
6 tasks done
fix: auto-detect GPUs in qwen3-4b script
#1700 opened Mar 10, 2026 by ailuntz Loading…
1
1
fix: make ray actor gpu fractions configurable
#1699 opened Mar 10, 2026 by ailuntz Loading…
1
1
fix: accept unboxed math answers
#1698 opened Mar 10, 2026 by ailuntz Loading…
1
1
fix: default reward for aborted samples
#1697 opened Mar 10, 2026 by ailuntz Loading…
1
1
fix: handle missing sglang cuda-graph constant
#1696 opened Mar 10, 2026 by ailuntz Loading…
1
1
PipelineRL -- keep cache on weight update
#1694 opened Mar 9, 2026 by hari-hm Loading…
1
[WIP] fix(cp): wrap linear attention CP in custom autograd.Function
#1692 opened Mar 9, 2026 by lilei199908 Loading…
1
fix: quote $MOE_LAYER_FREQ
#1689 opened Mar 8, 2026 by lawrence-harmonic Loading…
internv3.5 support
#1660 opened Mar 3, 2026 by samaritan1998 Loading…
fix: normalize rewards per-group when sample counts are unequal
#1655 opened Mar 2, 2026 by dubin555 Loading…
2 of 3 tasks
1
feat: Add knowledge distillation example with offline support
#1654 opened Mar 2, 2026 by tourzhao Loading…
3 tasks
Fix the Rotary Position Embedding (RoPE) parameter passing in the GLM5 mode
#1650 opened Mar 2, 2026 by hanxdmech-ship-it Loading…
[WIP] fix transforrmers api change at 5.2.0 run-ci-megatron
#1647 opened Feb 28, 2026 by UbeCc Loading…
Refactor code safety checks by removing patterns
#1643 opened Feb 28, 2026 by Rohan5commit Loading…
feat: add --lazy-multimodal-load to defer image process to rollout time
#1623 opened Feb 25, 2026 by yzlnew Loading…
2
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.