Skip to content

Pull requests: THUDM/slime

New pull request New
257 Open 1,591 Closed
257 Open 1,591 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

[ROCm] Update and unify ROCm support for gfx942 and gfx950
#2369 opened Sep 8, 2026 by LZ-QWQ Contributor Loading…
fix(args): reject --kl-coef with GRPO-family advantage estimators
#2368 opened Sep 8, 2026 by QJSQJS Loading…
fix: use group-level concurrency in fully-async rollout
#2367 opened Sep 7, 2026 by JayPritchet Loading…
fix(train): raise clear error when computed train_iters is 0
#2366 opened Sep 6, 2026 by Xuan-1998 • Draft
fix(data): fill sample requests across multiple epochs
#2365 opened Sep 6, 2026 by feng1201 Loading…
[docs] debug guide: tell a cold Triton compile from a colocate hang (en + zh)
#2364 opened Sep 6, 2026 by David553 Loading…
[Performance] Offload multimodal rollout preprocessing from the asyncio event loop
#2363 opened Sep 6, 2026 by Qi2yU Loading…
4 tasks done
1
fix(weight-sync): compose engine waves, credits and timeline
#2362 opened Sep 5, 2026 by 0z5a Loading…
1
fix(rollout): reject aborted samples before reward tensor
#2361 opened Sep 5, 2026 by YeonwooSung Loading…
1
fix(agent): realign from divergence using previous response length
#2360 opened Sep 5, 2026 by YeonwooSung Loading…
1
fix(args): reject --kl-coef for GRPO-style estimators
#2359 opened Sep 5, 2026 by YeonwooSung Loading…
1 task done
1
fix(sglang): tolerate missing CUDA graph memory tag
#2358 opened Sep 5, 2026 by YeonwooSung Loading…
1 task done
1
fix(rm): stop double-extracting boxed answers for boxed_math
#2357 opened Sep 5, 2026 by YeonwooSung Loading…
1
fix(whiten): scale-only path when shift_mean is false
#2356 opened Sep 5, 2026 by YeonwooSung Loading…
1
docs: fix flag help and fault-tolerance default values
#2355 opened Sep 5, 2026 by YeonwooSung Loading…
bench: add generic weight-sync policy sweep
#2354 opened Sep 4, 2026 by 0z5a Loading…
[profiling] Add trainer communication timeline
#2353 opened Sep 4, 2026 by 0z5a Loading…
feat(weight-sync): bound in-flight weight-sync buckets
#2352 opened Sep 4, 2026 by 0z5a Loading…
feat(weight-sync): add engine-group wave scheduling
#2351 opened Sep 4, 2026 by 0z5a Loading…
fix: cancel pending rollout tasks after a failure
#2350 opened Sep 4, 2026 by yuyz-cyber Loading…
5 tasks done
fix: avoid reading correction settings when TIS is disabled
#2349 opened Sep 4, 2026 by yuyz-cyber Loading…
4 tasks done
require --ref-load when KL is enabled instead of crashing with a TypeError
#2348 opened Sep 3, 2026 by rootkiller6788 Loading…
fix: preserve equals in extra environment values
#2346 opened Sep 3, 2026 by imshunsuke Loading…
fix(rollout): fix nested group sorting in fully async rollout
#2345 opened Sep 2, 2026 by looput Loading…
[cleanup] type BaseAdapter trajectory manager
#2343 opened Sep 1, 2026 by qshf Loading…
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.