Skip to content

Pull requests: sgl-project/sglang

New pull request New
777 Open 7,230 Closed
777 Open 7,230 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

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
#11709 opened Oct 16, 2025 by zejunchen-zejun Loading…
3
Support running FP4 Deepseek on SM120.
#11708 opened Oct 16, 2025 by weireweire Loading…
2 of 4 tasks
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 run-ci
#11702 opened Oct 16, 2025 by kevin85421 Loading…
1 of 4 tasks
[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
chore: bump SGLang version to 0.5.3.post3 run-ci
#11693 opened Oct 16, 2025 by sglang-bot Loading…
2
[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
10
[router] fix get_models endpoint for openai router run-ci
#11687 opened Oct 16, 2025 by key4ng Loading…
4 tasks
4
[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
9
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
2
[Router] Refactor protocol definitions: split spec.rs into modular files run-ci
#11677 opened Oct 15, 2025 by key4ng Loading…
4 tasks
28
[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
feat: return partial generation results when aborting requests in waiting queue run-ci
#11673 opened Oct 15, 2025 by guoyuhong Loading…
1 of 4 tasks
@fzyzcjy
3
[2/2] [feature] support openai like classification api in router run-ci
#11670 opened Oct 15, 2025 by whybeyoung Loading…
4
[RL] support weight updation with dp attention run-ci
#11669 opened Oct 15, 2025 by zhuzilin Loading…
1 of 4 tasks
@fzyzcjy
11
Manually flip deepep_mode for cuda_graph run-ci
#11666 opened Oct 15, 2025 by zhuzilin Loading…
1 of 4 tasks
@fzyzcjy
5
fix(glm45): disable reduce scatter
#11665 opened Oct 15, 2025 by jinmingyi1998 Loading…
3
WIP: Use trtllm_mla decode kernel for draft extend in speculative decoding run-ci
#11664 opened Oct 15, 2025 by Qiaolin-Yu Loading…
4 tasks
1
fix: bench_serving error with PD disaggregation run-ci
#11662 opened Oct 15, 2025 by Yi-sir Loading…
4 tasks
2
ProTip! Add no:assignee to see everything that’s not assigned.