Skip to content

Pull requests: sgl-project/sglang

New pull request New
1,098 Open 9,810 Closed
1,098 Open 9,810 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

[CI] Fix /rerun-stage command by using requests for workflow dispatch
#15447 opened Dec 19, 2025 by alisonshao Loading…
2 tasks
1
WIP: diffusion disagg diffusion SGLang Diffusion npu
#15445 opened Dec 19, 2025 by mickqian Loading…
6 tasks
1
[AMD][CI] Test new shadow runners in DO-NYC cluster amd run-ci
#15441 opened Dec 19, 2025 by sunxxuns Loading…
1
[WIP][Quantization][RL] Support Online Blockwise FP8 Quantization quant LLM Quantization reinforcement-learning run-ci
#15440 opened Dec 19, 2025 by AniZpZ Loading…
6 tasks
1
[HiCacheStorage] fix prefill bootstrap request host memory leaks
#15439 opened Dec 19, 2025 by MOHENOO Loading…
6 tasks
2
[diffusion] lora: fix generate_with_lora arg marshalling; add multi-lora batching test diffusion SGLang Diffusion lora
#15438 opened Dec 19, 2025 by chaos-gmi Loading…
1
[Auto Sync] Update scheduler_runtime_checker_mixin.py (20251219) run-ci
#15437 opened Dec 19, 2025 by merrymercy Loading…
2
[CI] Migrate CUDA Graph tests to test/registered/cuda_graph/ lora run-ci
#15436 opened Dec 19, 2025 by alisonshao Loading…
3 of 4 tasks
3
Qwen2.5-vl support SiluAndMul/GeluAndMul & Convert cu_seqlens to CPU for npu_flash_attention_unpad operator Multi-modal multi-modal language model
#15434 opened Dec 19, 2025 by xiaobaicxy Loading…
6 tasks
2
fix: unreachable error check in retraction run-ci
#15433 opened Dec 19, 2025 by alphabetc1 Loading…
6 tasks
3
[FusedMoE] Fix fuse dw13 tp sharded weight loading
#15432 opened Dec 19, 2025 by yinghai Loading…
6 tasks
1
Fix type mismatch in LoRA batch validation causing assertion failures
#15427 opened Dec 19, 2025 by ConnorLi96 Loading…
6 tasks
1
[chore]: improve time tracing of model loading process
#15426 opened Dec 19, 2025 by AndyDai-nv Loading…
6 tasks
1
Update readme documentation Improvements or additions to documentation run-ci
#15425 opened Dec 18, 2025 by merrymercy Loading…
2
Add customized sampler registration high priority run-ci
#15423 opened Dec 18, 2025 by Qiaolin-Yu Loading…
6 tasks
@ispobock
5
Draft: Flashinfer MOE FP8 support for Mistral Large 3. quant LLM Quantization
#15422 opened Dec 18, 2025 by dcampora Loading…
6 tasks
1
Support Heterogeneous KV cache quantization for different layers quant LLM Quantization
#15420 opened Dec 18, 2025 by jindajia Loading…
1 of 6 tasks
4
[WIP][diffusion] model: support Wan Animate diffusion SGLang Diffusion npu
#15419 opened Dec 18, 2025 by Mellonta Loading…
6 tasks
12
feat: Add limit-mm-data-per-request argument to server arguments documentation Improvements or additions to documentation run-ci
#15418 opened Dec 18, 2025 by JustinTong0323 Loading…
6 tasks
5
fix: update model name after weights update
#15416 opened Dec 18, 2025 by alphabetc1 Loading…
6 tasks
3
[AMD] Fix and add accuracy-test-2-gpu-amd back amd run-ci
#15415 opened Dec 18, 2025 by yctseng0211 Loading…
6 tasks done
1
[Minor] Remove deprecated tile_tokens_dim kwargs quant LLM Quantization
#15414 opened Dec 18, 2025 by DarkSharpness Loading…
6 tasks
2
fix(gateway): backward compatibility for GET endpoints model-gateway
#15413 opened Dec 18, 2025 by alphabetc1 Loading…
6 tasks
5
fuse ssm state store into chunk_gated_delta_rule_fwd_h run-ci
#15409 opened Dec 18, 2025 by yizhang2077 Loading…
6 tasks
5
[Diffusion] Add diffusion attention backends doc diffusion SGLang Diffusion documentation Improvements or additions to documentation
#15408 opened Dec 18, 2025 by BBuf Loading…
6 tasks
6
ProTip! What’s not been updated in a month: updated:<2025-11-18.