这是indexloc提供的服务，不要输入任何密码
Skip to content

Pull requests: THUDM/slime

New pull request New
Clear current search query, filters, and sorts
3 Open 78 Closed
3 Open 78 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

[doc][script] Add example script and docs for DeepSeek-R1
#104 by zhuzilin was merged Jul 25, 2025 Loading…
Tiny reduce num gpus for tests and add a train_async test
#103 by fzyzcjy was merged Jul 25, 2025 Loading…
Tiny fix test script error
#102 by fzyzcjy was merged Jul 25, 2025 Loading…
Refactor rollout generator to support abortable samples API
#101 by fzyzcjy was merged Jul 25, 2025 Loading…
Refactor multi-process wandb initialization logic
#100 by fzyzcjy was merged Jul 25, 2025 Loading…
Extract data source from Buffer
#99 by fzyzcjy was merged Jul 25, 2025 Loading…
Super tiny rename rollout generator and extract function to avoid name conflicts in future refactor
#98 by fzyzcjy was merged Jul 25, 2025 Loading…
Remove Buffer data pool
#97 by fzyzcjy was merged Jul 25, 2025 Loading…
5
Fix train_async error
#96 by fzyzcjy was merged Jul 25, 2025 Loading…
Tiny avoid hardcoding 8 gpus per node
#95 by fzyzcjy was merged Jul 25, 2025 Loading…
[model] support dpsk v3
#94 by zhuzilin was merged Jul 24, 2025 Loading…
Dump more data for visualization
#93 by fzyzcjy was merged Jul 23, 2025 Loading…
bugfix
#92 by zyzshishui was merged Jul 23, 2025 Loading…
refactor: extract weight updators from TrainRayActor
#91 by zhuzilin was merged Jul 22, 2025 Loading…
Tiny fix reward fn return a dict
#90 by fzyzcjy was merged Jul 23, 2025 Loading…
refactor: extract convert functions to folder
#89 by zhuzilin was merged Jul 22, 2025 Loading…
Tiny fix reward data type
#88 by fzyzcjy was merged Jul 22, 2025 Loading…
refactor: cleanup rollout buffer
#87 by zhuzilin was merged Jul 21, 2025 Loading…
refactor: rewrite rollout buffer doc
#86 by zhuzilin was merged Jul 21, 2025 Loading…
refactor: remove global var LOCAL_STORAGE
#84 by zhuzilin was merged Jul 21, 2025 Loading…
4
Tiny add assertion to avoid Megatron error
#82 by fzyzcjy was merged Jul 20, 2025 Loading…
refactor: optimize update_from_distributed to use fewer nccl group
#81 by zhuzilin was merged Jul 19, 2025 Loading…
Comment out DP Attention for run-qwen3-30B-A3B.sh
#79 by hebiao064 was closed Jul 18, 2025 Loading…
refactor: extract common data utils and add fsdp skeleton
#78 by zhuzilin was merged Jul 18, 2025 Loading…
refactor: extract a TrainRayActor base class
#76 by zhuzilin was merged Jul 18, 2025 Loading…
ProTip! Exclude everything labeled bug with -label:bug.