Skip to content

Pull requests: THUDM/slime

New pull request New
32 Open 822 Closed
32 Open 822 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

update sglang to 0.5.6 run-ci-precision run-ci-short
#1051 opened Dec 8, 2025 by lilei199908 Loading…
7
feat: Add Qwen3Moe backward kernel
#1050 opened Dec 8, 2025 by attack204 Loading…
Update sglang patch: add update_weights_from_tensor to EagleWorkerV2
#1044 opened Dec 6, 2025 by zhihengy Loading…
2
[Draft] Update Megatron patch to work for Megatron v0.15.0
#1042 opened Dec 6, 2025 by Birch-san Loading…
1
feat: Support list-of-dicts format for multimodal message content
#1037 opened Dec 5, 2025 by ppraneth Loading…
1
[ci] Add CI for save load ckpt run-ci-ckpt
#1036 opened Dec 5, 2025 by zhuzilin Loading…
Support Tau2 bench evalutation
#1025 opened Dec 4, 2025 by guapisolo • Draft
2
Add RLVE environment support & starter pack
#1020 opened Dec 3, 2025 by jbarnes850 Loading…
11
[WIP] Add quantization config -- make DSv3 torch_dist -> hf conversion work
#949 opened Nov 26, 2025 by vwxyzjn • Draft
RDMA Support for the weight transferring from Megatron to SGL
#932 opened Nov 25, 2025 by JensenFire • Draft
1 of 2 tasks
12
Add readable data logging
#871 opened Nov 24, 2025 by guapisolo Loading…
2
Optimize Memory Usage in Data Loading run-ci-short
#869 opened Nov 23, 2025 by lancerts Loading…
7
token-in-token-out and rollout log prob for fully async rl
#867 opened Nov 23, 2025 by rbao2018 Loading…
@yitianlian
5
[Feature/Fix] Support IPv6 host resolution and robust URI formatting
#859 opened Nov 21, 2025 by Chen-GX Loading…
feat(rollout): support evaluation parameter in custom generate function
#832 opened Nov 19, 2025 by bcol23 Loading…
change PYTHONBUFFERED to PYTHONUNBUFFERED
#724 opened Nov 14, 2025 by ad8e Loading…
1
[WIP] Support SimpleTir
#701 opened Nov 8, 2025 by zyzshishui • Draft
1
Optimize data.py for efficient data loading
#696 opened Nov 6, 2025 by ppraneth Loading…
2
perf: Add pipelined weight update via --pipeline-update flag
#689 opened Nov 5, 2025 by GeLee-Q Loading…
5
feat: Add CISPO (Clipped IS-weight Policy Optimization)
#681 opened Nov 3, 2025 by kekmodel Loading…
1
[FSDP] Add an example script to run 4B demo with fsdp
#672 opened Nov 2, 2025 by Zhuohao-Li Loading…
3
Avoiding multiple ranks write into debug train data file concurrently
#642 opened Oct 30, 2025 by YuchenFan48 Loading…
7
[Feature] Add sglang server metrics in wandb logging
#604 opened Oct 27, 2025 by yitianlian Loading…
6
Support effective batch filtering
#547 opened Oct 21, 2025 by sam571128 Loading…
Support advantage normalization and loss aggregation options
#545 opened Oct 21, 2025 by sam571128 Loading…
1
ProTip! Follow long discussions with comments:>50.