Skip to content

Pull requests: sgl-project/sglang

New pull request New
1,018 Open 9,313 Closed
1,018 Open 9,313 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: adding fallback for incomplete tokenizer cache
#14762 opened Dec 9, 2025 by dougyster Loading…
1 task
1
fix: race condition between validation and download locks
#14761 opened Dec 9, 2025 by alisonshao Loading…
2 tasks
1
2
[Auto Sync] Update data_parallel_controller.py, detokenizer... (20251209) run-ci
#14759 opened Dec 9, 2025 by merrymercy Loading…
2
fix: adding retries for weight corruption
#14757 opened Dec 9, 2025 by dougyster Loading…
1 task
7
fix: adding rate limit warning at verify token permission stage
#14756 opened Dec 9, 2025 by dougyster Loading…
1 task
4
Eagle: GPT-OSS Eagle v2 support
#14755 opened Dec 9, 2025 by IzzyPutterman Loading…
6 tasks
4
[Tool Call][DSV32] Streamline function call parameters deepseek
#14750 opened Dec 9, 2025 by Muqi1029 Loading…
2 of 6 tasks
@JustinTong0323
6
[Tool Call] Add Parallel tool calls request param
#14749 opened Dec 9, 2025 by Muqi1029 Loading…
2 of 6 tasks
fix: handle Jinja2 template errors as client errors in OpenAIServingChat run-ci
#14748 opened Dec 9, 2025 by JustinTong0323 Loading…
6 tasks
1
4
Re-add the API serving timing metrics. run-ci
#14744 opened Dec 9, 2025 by hnyls2002 Loading…
7
Fix spec info's filter when reqs are finished right after prefill
#14742 opened Dec 9, 2025 by hnyls2002 Loading…
1
3
[1/N][Sparse With Hicache]: Add Sparse Interface deepseek run-ci
#14741 opened Dec 9, 2025 by hzh0425 • Draft
6 tasks
9
scheduler: correct load metric
#14737 opened Dec 9, 2025 by sufeng-buaa Loading…
1 of 6 tasks
3
[NPU] Support w4a8 with activation clip npu
#14736 opened Dec 9, 2025 by jiaming1130 Loading…
6 tasks
@ping1jing2
3
Fix: ReasonerGrammarBackend can handle tokenizer that does not have "think_end_id" as attribute. (ex: GLM 4.6)
#14731 opened Dec 9, 2025 by gmlwns2000 Loading…
7
[Feat] Async KV transfer for PD disaggregation amd blackwell SM100/SM120 deepseek dependencies Pull requests that update a dependency file diffusion SGLang Diffusion documentation Improvements or additions to documentation hicache Hierarchical Caching for SGLang lora model-gateway Multi-modal multi-modal language model npu quant LLM Quantization sgl-kernel
#14730 opened Dec 9, 2025 by Kevin-XiongC • Draft
Feat/wna16moe deepseek
#14727 opened Dec 9, 2025 by pbkowalski Loading…
4
Use bootstrap server to sync prefill dp rank documentation Improvements or additions to documentation
#14726 opened Dec 9, 2025 by changhuaixin Loading…
1 of 6 tasks
@hnyls2002 @ShangmingCai
4
fix server args bug
#14725 opened Dec 9, 2025 by TomerBN-Nvidia Loading…
6 tasks
1
[DLLM] Add CI for diffusion LLMs
#14723 opened Dec 9, 2025 by ClawSeven Loading…
4 of 6 tasks
3
[CI test] amd run-ci
#14722 opened Dec 9, 2025 by sunxxuns Loading…
2 tasks
3
[GLM-4.6V] Support Pipeline Parallelism for GLM-4.6V & GLM-4.1V Multi-modal multi-modal language model performance run-ci vlm
#14720 opened Dec 9, 2025 by yuan-luo Loading…
6 tasks
13
Bugfix: Writing to storage when write-back method is chosen
#14718 opened Dec 9, 2025 by MMuzzammil1 Loading…
2 of 6 tasks
1
3
[diffusion] kernel fusion: add layernorm scale shift fusion for Wan and Qwen-Image models diffusion SGLang Diffusion sgl-kernel
#14717 opened Dec 9, 2025 by jianyingzhu Loading…
6 tasks
10
Tiny support customizing Prometheus duration buckets model-gateway run-ci
#14716 opened Dec 9, 2025 by fzyzcjy Loading…
6 tasks
2
ProTip! Type g i on any issue or pull request to go back to the issue listing page.