Skip to content

Pull requests: sgl-project/sglang

New pull request New
770 Open 7,253 Closed
770 Open 7,253 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

[Auto Sync] Update scheduler.py (20251017) high priority run-ci
#11738 opened Oct 17, 2025 by zhyncs Loading…
@hnyls2002
3
support cutlass fp4 kernel in sm120
#11737 opened Oct 17, 2025 by AichenF Loading…
5
Revert "Set csgmv as default lora backend. (#11488)" high priority run-ci
#11735 opened Oct 16, 2025 by zhyncs Loading…
4 tasks
@lifuhuang @zhyncs @Fridge003
9
chore: bump sgl-kernel version to 0.3.16.post3 run-ci
#11733 opened Oct 16, 2025 by sglang-bot Loading…
5
add tuned fuse moe kernel for qwen3 235b fp8 on h200
#11730 opened Oct 16, 2025 by pdasgup Loading…
4 tasks
@JustinTong0323
5
[overlap-spec] Make plan stream an option run-ci
#11724 opened Oct 16, 2025 by hnyls2002 Loading…
3
[router] Support multiple worker URLs for OpenAI router run-ci
#11723 opened Oct 16, 2025 by key4ng • Draft
4 tasks
8
Support mrope triton kernel and add unit test run-ci
#11722 opened Oct 16, 2025 by yuan-luo Loading…
4 tasks
8
bucket policy
#11719 opened Oct 16, 2025 by syy-hw • Draft
4 tasks
[WIP][sgl-kernel] support flashmla libtorch high priority run-ci
#11717 opened Oct 16, 2025 by FlamingoPg Loading…
1 of 4 tasks
@FlamingoPg @Fridge003
10
try to support sgl-kernel in piecewise-cuda-graph run-ci
#11716 opened Oct 16, 2025 by BBuf • Draft
[Feature] Refactor sampling_params
#11713 opened Oct 16, 2025 by Muqi1029 Loading…
1 of 4 tasks
5
enable ut test for xpu devices run-ci
#11712 opened Oct 16, 2025 by DiweiSun • Draft
4 tasks
feat(example/fastapi): support --startup-timeout using Qwen3-Next-80B-A3B-Instruct as example
#11710 opened Oct 16, 2025 by Kindyaa Loading…
4 tasks
3
[Fix] fix type issue of env flag value MODELOPT_MAX_TOKENS_PER_EXPERT run-ci
#11709 opened Oct 16, 2025 by zejunchen-zejun Loading…
@FlamingoPg
3
Support running FP4 Deepseek on SM120. run-ci
#11708 opened Oct 16, 2025 by weireweire Loading…
2 of 4 tasks
@FlamingoPg
4
[sgl-kernel] enhance sgl-kernel import logic for sm8x run-ci
#11707 opened Oct 16, 2025 by FlamingoPg Loading…
1 of 4 tasks
@FlamingoPg @zhyncs
3
[quantization][MoE] fix the check for tp_size / moe_ep_size / moe_intermediate_size / weight_block_size_n express-lane A PR may be merged without a full CI check run-ci
#11702 opened Oct 16, 2025 by kevin85421 Loading…
1 of 4 tasks
@mickqian
[Test] support llm-compressor: w8a8_fp8_block, wNa16
#11701 opened Oct 16, 2025 by Wangzheee Loading…
4 tasks
1
bench: support video-mme run-ci
#11695 opened Oct 16, 2025 by mickqian Loading…
4 tasks
1
[router] Add Configurable L0 and L1 Tokenizer Caching enhancement New feature or request router router-benchmark run-ci
#11688 opened Oct 16, 2025 by slin1237 Loading…
2 of 4 tasks
19
[Lint] Add python/sglang to ruff F401 checks and remove unused imports in files run-ci
#11685 opened Oct 15, 2025 by CatherineSue Loading…
1 of 4 tasks
@zhyncs
14
wip: Remove redundant fill_(0) in dp_scatter run-ci
#11683 opened Oct 15, 2025 by ch-wan Loading…
4 tasks
3
Cleaning indexer for DeepSeek V3.2 run-ci
#11682 opened Oct 15, 2025 by Fridge003 Loading…
4 tasks
@zhyncs
2
[Bug fix] fix Qwen3-VL dense model launch failure caused by rotary-embedding
#11675 opened Oct 15, 2025 by coco-alen Loading…
4 tasks
4
ProTip! Mix and match filters to narrow down what you’re looking for.