Skip to content

Pull requests: sgl-project/sglang

New pull request New
2,872 Open 18,906 Closed
2,872 Open 18,906 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 Stage B CUDA CI
#28367 opened Jun 16, 2026 by b8zhong Collaborator Loading…
3
[diffusion] Fuse tanh-GELU into shared MLP FFN up-proj GEMM epilogue diffusion SGLang Diffusion
#28366 opened Jun 16, 2026 by BBuf Collaborator Loading…
3 of 4 tasks
1
[Scheduler] Add SLA-constrained dynamic batching for adaptive decode throughput
#28365 opened Jun 16, 2026 by MissyLee2018 Loading…
5 tasks
2
[core] Gate the overlap WAR barrier on forward reads to recover decode throughput
#28363 opened Jun 16, 2026 by hnyls2002 Collaborator Loading…
1
[AMD] moe_shared_gate_residual_fuse: MoE Shared-Expert Sigmoid Gate + Residual Add jit-kernel
#28362 opened Jun 16, 2026 by yichiche Collaborator Loading…
3 tasks done
1
[AMD] gdn_qk_l2norm_fuse: GatedDeltaNet Q/K L2Norm Fusion jit-kernel
#28361 opened Jun 16, 2026 by yichiche Collaborator Loading…
3 tasks done
1
[AMD] Fix AITER Scout workflow permissions amd
#28360 opened Jun 16, 2026 by yctseng0211 Collaborator Loading…
1
Markdown format modification deepseek documentation Improvements or additions to documentation hicache Hierarchical Caching for SGLang lora Multi-modal multi-modal language model npu quant LLM Quantization speculative-decoding
#28359 opened Jun 16, 2026 by a60124901 Loading…
5 tasks
4
[AMD] fix(jit): port kv_canary write/verify/plan kernels to ROCm jit-kernel
#28357 opened Jun 16, 2026 by michaelzhang-ai Collaborator Loading…
2 of 3 tasks
1
[AMD] Fix AITER Scout workflow permissions amd
#28356 opened Jun 16, 2026 by bingxche Collaborator • Draft
1
feat: add FlashInfer cutlass FP8 block-scale MoE backend for Qwen3.5
#28355 opened Jun 16, 2026 by anish-shanbhag • Draft
1
Support FlashInfer CuTe DSL NVFP4 MoE quantization blackwell SM100/SM120 deepseek quant LLM Quantization
#28354 opened Jun 16, 2026 by zianglih Contributor • Draft
3 of 5 tasks
1
docs(cookbook): migrate Gemma4 to the config-driven template documentation Improvements or additions to documentation
#28353 opened Jun 15, 2026 by zijiexia Collaborator Loading…
2
docs(cookbook): migrate MiniMax-M2.7 to the config-driven template documentation Improvements or additions to documentation
#28352 opened Jun 15, 2026 by zijiexia Collaborator Loading…
2
docs(cookbook): migrate Nemotron3-Ultra to the config-driven template documentation Improvements or additions to documentation
#28351 opened Jun 15, 2026 by zijiexia Collaborator Loading…
2
docs(cookbook): migrate GLM-5.1 to the config-driven template documentation Improvements or additions to documentation
#28350 opened Jun 15, 2026 by zijiexia Collaborator Loading…
2
[AMD]: Enable NIXL PD disaggregation for ROCm(1/n) amd
#28348 opened Jun 15, 2026 by Lzy17 Contributor Loading…
5 tasks
1
Revert Gemma4 modelopt fp4 MoE backend change
#28347 opened Jun 15, 2026 by mmangkad Collaborator Loading…
1
Use Flashinfer allreduce fusion for MNNVL allreduce for Nemotron jit-kernel
#28346 opened Jun 15, 2026 by b8zhong Collaborator • Draft
1
[AMD] Make HIP capability probes import-safe when no HIP GPU is visible
#28345 opened Jun 15, 2026 by XinyuJiangCMU Contributor Loading…
1
[AMD] register 6 2-gpu tests to stage-b-test-2-gpu-large-amd run-ci
#28344 opened Jun 15, 2026 by michaelzhang-ai Collaborator Loading…
1
[Kimi K2.5] Fix eagle3 aux capture for tp>1 when AR fusion is enabled deepseek
#28343 opened Jun 15, 2026 by kpham-sgl Collaborator Loading…
5 tasks done
1
[Tokenizer] Fix abort racing server crash when large amount of aborts bypass-fastfail run-ci run-ci-extra
#28341 opened Jun 15, 2026 by hanming-lu Collaborator Loading…
5 tasks
2
Precompute FP8 KV cache inverse scales to drop per-forward reciprocal kernels blackwell SM100/SM120
#28339 opened Jun 15, 2026 by vschandramourya Loading…
3 tasks done
1
docs: add Amazon SageMaker AI deployment guide documentation Improvements or additions to documentation
#28338 opened Jun 15, 2026 by Jyothirmaikottu Loading…
2 tasks done
1
ProTip! Type g i on any issue or pull request to go back to the issue listing page.