Skip to content

Pull requests: THUDM/slime

New pull request New
59 Open 931 Closed
59 Open 931 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

feat: add custom pg_loss reducer
#1235 opened Dec 26, 2025 by ChangyiYang Loading…
optimize VLM processing run-ci-short
#1234 opened Dec 26, 2025 by nanjiangwill Loading…
[Fix][VLM] Fix image_patch_size for vision preprocessing
#1227 opened Dec 26, 2025 by coding-famer Loading…
Handle deepscaler answers without markers
#1226 opened Dec 26, 2025 by cklxx Loading…
1
update default paths and disable offloading for AMD qwen3-4B training
#1225 opened Dec 26, 2025 by Vivicai1005 Loading…
[Feature] Add CI for fault tolerance run-ci-short
#1222 opened Dec 26, 2025 by yitianlian Loading…
2
Add Qwen3-Coder-30B-A3B-Instruct model script
#1213 opened Dec 25, 2025 by maoquan-ms Loading…
Megatron VLM Support (Qwen2.5-VL series) (3/N)
#1210 opened Dec 25, 2025 by Zhuohao-Li Loading…
Fix ruff hook and update pre-commit hooks
#1206 opened Dec 24, 2025 by ParagEkbote Loading…
Feat/router pr pt1
#1203 opened Dec 24, 2025 by ChangyiYang • Draft
fix: replace blocking sleep with async sleep and fix file handle leak
#1200 opened Dec 24, 2025 by lancerts Loading…
1
minor fix test scripts, add default value
#1199 opened Dec 23, 2025 by yueming-yuan • Draft
update quick start doc
#1193 opened Dec 23, 2025 by zijiexia Loading…
1
Integrate Sonic-Moe in FSDP
#1176 opened Dec 22, 2025 by ChangyiYang • Draft
2
[feature] update fp8 weight from megatron fp8 tensor
#1173 opened Dec 21, 2025 by fy1214 • Draft
[FEATURE] support Int4 qat in slime
#1172 opened Dec 21, 2025 by fy1214 Loading…
[WIP] Implement RDMA P2P weight update using TransferEngine
#1164 opened Dec 20, 2025 by JD-ETH Loading…
7
[FEATURE] Add tool call support for multi-turn SFT with delta-based loss masking
#1159 opened Dec 20, 2025 by Surya-Gunukula Loading…
tau-bench: offline stub user + tool parsing fallback
#1158 opened Dec 19, 2025 by Fengzdadi Loading…
Add tau2-bench training cookbook and implementation
#1156 opened Dec 19, 2025 by jbarnes850 Loading…
17
fix: fix 8B VLM true on policy issue run-ci-short
#1155 opened Dec 19, 2025 by nanjiangwill Loading…
1
[WIP] Add TerminalBench eval delegate + quickstart
#1154 opened Dec 19, 2025 by XinyuJiangCMU • Draft
6 tasks done
[VLM] Multi-turn with Sokoban Dataset
#1141 opened Dec 17, 2025 by gxlvera • Draft
9 of 12 tasks
7
[FSDP][1/n] Support LoRA training for FSDP backend.
#1140 opened Dec 17, 2025 by GuanxingLu Loading…
4 tasks
17
[On Policy Distillation] resolve log prob dimension mismatch in on-policy distillation with CP > 1
#1135 opened Dec 17, 2025 by Yuchen-Cao Loading…
5
ProTip! Adding no:label will show everything without a label.