Skip to content

Pull requests: THUDM/slime

New pull request New
78 Open 1,177 Closed
78 Open 1,177 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

[cleanup] remove metric checker and long tests run-ci-megatron
#1603 opened Feb 20, 2026 by zhuzilin Loading…
Fix pipeline parallel and multimodal input handling for Kimi-VL
#1598 opened Feb 19, 2026 by Chokoyo • Draft
Add Kimi-VL/K25 Megatron-HF conversion support
#1597 opened Feb 19, 2026 by Chokoyo • Draft
[Feature] Add configurable arguments for rollout manager actor
#1596 opened Feb 18, 2026 by TSunny007 Loading…
[Feature] Add curriculum learning example with dynamic multi-task training and online prompt filtering
#1594 opened Feb 18, 2026 by zhangzx-uiuc Loading…
1
[Fix] Minor fix for properly finishing / flushing wandb logging metrics at exit
#1592 opened Feb 17, 2026 by silunw Loading…
1
[Feature] Add modular tracking interface with MLflow backend
#1591 opened Feb 17, 2026 by mouad-hpc Loading…
4 tasks done
2
Upgrade GitHub Actions for Node 24 compatibility
#1590 opened Feb 14, 2026 by salmanmkc Loading…
fix: restrict SymPy parser scope to prevent arbitrary code execution
#1587 opened Feb 13, 2026 by Hardik-369 Loading…
1
7
Add retries to the Remote Reward Model, do not fail on connection drops or endpoint instability
#1582 opened Feb 12, 2026 by joyliu-q Loading…
add rollout_data to rollout_data_postprocess
#1581 opened Feb 12, 2026 by zui-jiang Loading…
[Fix] Add missing space between --save and extra_args in convert_checkpoint
#1580 opened Feb 12, 2026 by kaysonyu Loading…
1 task done
fix: Handle IPv6 addresses in weight sync init_method
#1576 opened Feb 11, 2026 by zx3xyy Loading…
Support qwen3-next MTP Training
#1575 opened Feb 11, 2026 by zx3xyy Loading…
13
fix issue#1558, --load with restoring megatron checkpoint but rollout start with 0
#1571 opened Feb 11, 2026 by p1k0pan Loading…
Sglang rollout timeout, refer to issue #1562
#1570 opened Feb 11, 2026 by p1k0pan Loading…
[Feature] Trust region rejection sampling
#1568 opened Feb 10, 2026 by LeonEricsson Loading…
1 task
add no colocate update critic only run-ci-megatron
#1567 opened Feb 10, 2026 by lilei199908 Loading…
5
Add quantization support for bridge mode weight update
#1564 opened Feb 9, 2026 by jairuigou Loading…
[docs] fix reproducibility.md translation
#1560 opened Feb 8, 2026 by lckr Loading…
fix: fix nvidia-modelopt version specifier in build_conda.sh
#1554 opened Feb 6, 2026 by liujiahua123123 Loading…
fix: remove double-counting of LR scheduler steps on checkpoint resume
#1547 opened Feb 5, 2026 by Surya-Gunukula Loading…
Fix: convert kimi int4 to bf16
#1541 opened Feb 3, 2026 by Gao016 Loading…
Add bridge mode support for distributed weight update
#1537 opened Feb 3, 2026 by coding-famer Loading…
add weight convert for kimi_vl
#1532 opened Feb 2, 2026 by GeLee-Q • Draft
ProTip! Follow long discussions with comments:>50.