Skip to content

Pull requests: sgl-project/sglang

New pull request New
1,472 Open 11,562 Closed
1,472 Open 11,562 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

[NPU] support dsv32 radixcache on ascend Refactor npu
#17964 opened Jan 30, 2026 by khalil2ji3mp6 Loading…
5 tasks
1
[AMD] Add build for ROCm 7.2 preview images amd
#17962 opened Jan 30, 2026 by akao-amd Loading…
5 tasks
5
fix(ollama): preserve content in stream=true when max_new_tokens is tiny
#17961 opened Jan 30, 2026 by jadidbourbaki Loading…
1
Fix rerun stage command with merged commit history
#17960 opened Jan 29, 2026 by Kangyan-Zhou Loading…
5 tasks
4
ROCm (gfx1100): sgl-kernel HIP enablement amd dependencies Pull requests that update a dependency file sgl-kernel
#17958 opened Jan 29, 2026 by ljubomirj Loading…
4
ROCm (gfx1100): AWQ/GLM4 fixes, vllm fallbacks, dtype fixes amd dependencies Pull requests that update a dependency file quant LLM Quantization sgl-kernel
#17957 opened Jan 29, 2026 by ljubomirj Loading…
1
[Liquid AI] Support LFM VL deepseek diffusion SGLang Diffusion Multi-modal multi-modal language model quant LLM Quantization
#17954 opened Jan 29, 2026 by vincentzed Loading…
1 of 5 tasks
6
[AMD] support two batch overlapping for mori ep deepseek documentation Improvements or additions to documentation
#17953 opened Jan 29, 2026 by billishyahao Loading…
5 tasks
6
Add A3 8/16-NPU runners, constant file and test cases for basic functional parameters, LLM and multimodal models & API deepseek Multi-modal multi-modal language model npu
#17952 opened Jan 29, 2026 by Sugar920 Loading…
5 tasks
10
Direct model loading from object storage with Runai Model Streamer documentation Improvements or additions to documentation
#17948 opened Jan 29, 2026 by noa-neria Loading…
7
[MUSA][8/N] Port CUDA kernels that are compatible with MUSA dependencies Pull requests that update a dependency file mthreads quant LLM Quantization sgl-kernel
#17946 opened Jan 29, 2026 by yafengio Loading…
3 of 5 tasks
11
Do online fp8 quantization while loading weights instead of in process_weights_after_loading, reducing memory overhead quant LLM Quantization
#17945 opened Jan 29, 2026 by fxmarty-amd Loading…
1 of 2 tasks
2
10
[diffusion] Fix b64 Output logic diffusion SGLang Diffusion
#17944 opened Jan 29, 2026 by varadrane1707 Loading…
2 of 5 tasks
9
【docs】【Ascend】Update Expert Parallelism docs for Ascend NPU documentation Improvements or additions to documentation
#17940 opened Jan 29, 2026 by husf1130 Loading…
5 tasks
7
Support passing spaces_between_special_tokens per request
#17939 opened Jan 29, 2026 by RunningLeon Loading…
5 tasks
3
feat: add reasoning tokens in usage info
#17938 opened Jan 29, 2026 by jimmy-evo Loading…
5 tasks
@JustinTong0323
5
[diffusion]Allows quality adjustment of generated images/videos through requests. diffusion SGLang Diffusion run-ci
#17937 opened Jan 29, 2026 by IPostYellow Loading…
5 tasks
11
[Kernel] Add JIT rotary_embedding_kernel
#17934 opened Jan 29, 2026 by pansicheng Loading…
5 tasks
15
[DLLM] Fix dllm bug in scheduler run-ci
#17932 opened Jan 29, 2026 by ClawSeven Loading…
5 tasks
5
support fused_moe_triton and moe_sum_all_reduce kernel fusion[reduce 20-30% TTFT]
#17931 opened Jan 29, 2026 by xieminghe1 Loading…
5 tasks
4
Fix SHM pointer re-serialization in DP attention. run-ci
#17930 opened Jan 29, 2026 by FlamingoPg Loading…
2 of 5 tasks
1
@FlamingoPg
9
fix: zmq_to_tokenizer encoder transfer when host listens to 0.0.0.0
#17929 opened Jan 29, 2026 by RangerCD Loading…
5 tasks
1
[Refactor] [Diffusion] Refactor custom ops diffusion SGLang Diffusion
#17928 opened Jan 29, 2026 by Makcum888e • Draft
2 of 5 tasks
9
feat: Add ModelScope support for multimodal_gen models diffusion SGLang Diffusion
#17924 opened Jan 29, 2026 by yrk111222 Loading…
2 of 5 tasks
10
adapt MODELSCOPE download run-ci
#17922 opened Jan 29, 2026 by Hide-on-bushsh Loading…
5 tasks
2
ProTip! Adding no:label will show everything without a label.