Skip to content

Pull requests: sgl-project/sglang

New pull request New
1,031 Open 9,336 Closed
1,031 Open 9,336 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

fix(lora): add run_lora_a_embedding to ChunkedSgmvLoRABackend lora
#14805 opened Dec 10, 2025 by ashtonchew Loading…
6 of 7 tasks
1
4
Support zai-org/AutoGLM-Phone-9B
#14804 opened Dec 10, 2025 by yeahdongcn Loading…
6 tasks
3
[Feature] Add pyproject_rocm.toml for end-to-end ROCm pip installation support amd dependencies Pull requests that update a dependency file documentation Improvements or additions to documentation
#14802 opened Dec 10, 2025 by RohitNagraj • Draft
2 of 4 tasks
2
Revert transformers to 4.57.1 deepseek dependencies Pull requests that update a dependency file run-ci
#14801 opened Dec 10, 2025 by yhyang201 Loading…
6 tasks
8
Fix user rate limit check run-ci
#14799 opened Dec 10, 2025 by Kangyan-Zhou Loading…
6 tasks
2
fix lora target all + csgmv backend run-ci
#14796 opened Dec 10, 2025 by b8zhong Loading…
1
2
Feature/Fix multi lora scheduler blocking issue and PIN None LoRA traffic
#14795 opened Dec 10, 2025 by ConnorLi96 Loading…
2 tasks
1
[Difussion] Refactor diffusion fuse qkv and support qwen-image diffusion SGLang Diffusion run-ci
#14793 opened Dec 10, 2025 by BBuf Loading…
6 tasks
2
[Qwen3-next] Prefix cache for qwen3-next npu
#14792 opened Dec 10, 2025 by hanming-lu • Draft
6 tasks
1
[hotfix]: Add missing args for 3FS bench_client.py run-ci
#14791 opened Dec 10, 2025 by hzh0425 Loading…
6 tasks
@xiezhq-hermann
1
[PD][Feat]: add SJF (Shortest Job First) scheduling policy documentation Improvements or additions to documentation
#14789 opened Dec 10, 2025 by qianlihuang Loading…
4 of 6 tasks
3
[CI] Use temporary log directory in test_vlm_models to avoid reading cached results (#14760) Multi-modal multi-modal language model
#14787 opened Dec 10, 2025 by maomao123321 Loading…
5 tasks
1
[Feat] Async KV transfer for PD disaggregation
#14782 opened Dec 10, 2025 by Kevin-XiongC Loading…
1 of 6 tasks
2
[Performance] optimize NSA backend metadata computation for multi-step speculative decoding
#14781 opened Dec 10, 2025 by Johnsonms Loading…
6
feat: add Step-Audio-2 model support
#14780 opened Dec 10, 2025 by shuaills Loading…
6 tasks
1
CI: adding errors to Github summary
#14778 opened Dec 10, 2025 by dougyster Loading…
7
[Proposal] Memory-semantic PD-disaggregation paradigm
#14775 opened Dec 10, 2025 by foraxe Loading…
3 of 6 tasks
1
Add TLS/SSL support for HTTP server and mTLS for sgl-router documentation Improvements or additions to documentation
#14774 opened Dec 10, 2025 by Kangyan-Zhou • Draft
6 tasks
1
Add retry logic for scheduled CI tests enable-retry Enable retry logic for CI tests run-ci
#14771 opened Dec 10, 2025 by alisonshao Loading…
2 of 3 tasks
2
[Router-GO] implement a Go SGLang Router - OpenAI Compatible API Server documentation Improvements or additions to documentation model-gateway run-ci
#14770 opened Dec 10, 2025 by whybeyoung Loading…
1
[CI] Reduce stage-b auto-partition from 4 to 1 run-ci
#14769 opened Dec 10, 2025 by alisonshao Loading…
7
fix: adding fallback for multimodal_gen tokenizer loader diffusion SGLang Diffusion
#14767 opened Dec 10, 2025 by dougyster Loading…
1 task
3
Gigachat 3 tool parser and tests documentation Improvements or additions to documentation
#14765 opened Dec 10, 2025 by ajpqs Loading…
3 of 6 tasks
1
Enable TRT Allreduce Fusion by default for compatible models run-ci
#14764 opened Dec 10, 2025 by b8zhong Loading…
5
fix: adding fallback for incomplete tokenizer cache run-ci
#14762 opened Dec 9, 2025 by dougyster Loading…
1 task
4
ProTip! Filter pull requests by the default branch with base:main.