Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Appearance settings

Pull requests: THUDM/slime

New pull request New
51 Open 907 Closed
51 Open 907 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

[Featuren] Change default value of rollout health check
#1197 opened Dec 23, 2025 by yitianlian Loading…
update quick start doc
#1193 opened Dec 23, 2025 by zijiexia Loading…
1
update default paths for AMD script to support out-of-the-box execution
#1191 opened Dec 23, 2025 by Vivicai1005 Loading…
Integrate Sonic-Moe in FSDP
#1176 opened Dec 22, 2025 by ChangyiYang • Draft
[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…
5
[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
5 tasks
[WIP] Megatron VLM Support w/ SFT (2/N)
#1150 opened Dec 19, 2025 by Zhuohao-Li Loading…
[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…
3
Fix bug in dapo reward
#1134 opened Dec 16, 2025 by ChangyiYang Loading…
2
[FSDP] Support Qwen3-30B-A3B and analyse memory usage
#1132 opened Dec 16, 2025 by mingMelody Loading…
3 tasks done
1
5
[on-policy distillation] update reward function to fix potential token mismatches
#1128 opened Dec 16, 2025 by ahxt Loading…
Optimize CP loss communication
#1102 opened Dec 12, 2025 by cklxx • Draft
fix: resolve size mismatch error during training (fixes #1076)
#1085 opened Dec 11, 2025 by fangzhensheng Loading…
1
1
[WIP][FSDP] implement calculate_per_token_loss=True
#1055 opened Dec 8, 2025 by peterjc123 • Draft
Update sglang patch: add update_weights_from_tensor to EagleWorkerV2
#1044 opened Dec 6, 2025 by zhihengy Loading…
3
[Draft] Update Megatron patch to work for Megatron v0.15.0
#1042 opened Dec 6, 2025 by Birch-san Loading…
2
feat: Support list-of-dicts format for multimodal message content
#1037 opened Dec 5, 2025 by ppraneth Loading…
1
ProTip! What’s not been updated in a month: updated:<2025-11-23.
Morty Proxy This is a proxified and sanitized view of the page, visit original site.