Pull requests: sgl-project/sglang

New pull request New

772 Open 7,229 Closed

Pull requests list

Support running FP4 Deepseek on SM120.

#11708 opened Oct 16, 2025 by weireweire

4 tasks

[sgl-kernel] enhance sgl-kernel import logic for sm8x run-ci

#11707 opened Oct 16, 2025 by FlamingoPg

1 of 4 tasks

@FlamingoPg @zhyncs

[quantization][MoE] fix the check for tp_size / moe_ep_size / moe_intermediate_size / weight_block_size_n run-ci

#11702 opened Oct 16, 2025 by kevin85421

1 of 4 tasks

[Test] support llm-compressor: w8a8_fp8_block, wNa16

#11701 opened Oct 16, 2025 by Wangzheee

4 tasks

bench: support video-mme run-ci

#11695 opened Oct 16, 2025 by mickqian

4 tasks

chore: bump SGLang version to 0.5.3.post3 run-ci

#11693 opened Oct 16, 2025 by sglang-bot

[router] Add Configurable L0 and L1 Tokenizer Caching enhancement router router-benchmark run-ci

#11688 opened Oct 16, 2025 by slin1237

2 of 4 tasks

[router] fix get_models endpoint for openai router run-ci

#11687 opened Oct 16, 2025 by key4ng

4 tasks

[Lint] Add python/sglang to ruff F401 checks and remove unused imports in files run-ci

#11685 opened Oct 15, 2025 by CatherineSue

1 of 4 tasks

wip: Remove redundant fill_(0) in dp_scatter run-ci

#11683 opened Oct 15, 2025 by ch-wan

4 tasks

Cleaning indexer for DeepSeek V3.2 run-ci

#11682 opened Oct 15, 2025 by Fridge003

4 tasks

[Router] Refactor protocol definitions: split spec.rs into modular files run-ci

#11677 opened Oct 15, 2025 by key4ng

4 tasks

[Bug fix] fix Qwen3-VL dense model launch failure caused by rotary-embedding

#11675 opened Oct 15, 2025 by coco-alen

4 tasks

feat: return partial generation results when aborting requests in waiting queue run-ci

#11673 opened Oct 15, 2025 by guoyuhong

1 of 4 tasks

@fzyzcjy

[2/2] [feature] support openai like classification api in router run-ci

#11670 opened Oct 15, 2025 by whybeyoung

[RL] support weight updation with dp attention run-ci

#11669 opened Oct 15, 2025 by zhuzilin

1 of 4 tasks

@fzyzcjy

Manually flip deepep_mode for cuda_graph run-ci

#11666 opened Oct 15, 2025 by zhuzilin

1 of 4 tasks

@fzyzcjy

fix(glm45): disable reduce scatter

#11665 opened Oct 15, 2025 by jinmingyi1998

WIP: Use trtllm_mla decode kernel for draft extend in speculative decoding run-ci

#11664 opened Oct 15, 2025 by Qiaolin-Yu

4 tasks

fix: bench_serving error with PD disaggregation run-ci

#11662 opened Oct 15, 2025 by Yi-sir

4 tasks

fix: replace buggy flashinfer fp4 gemm with sgl-kernel fp4 gemm run-ci

#11661 opened Oct 15, 2025 by Qiaolin-Yu

4 tasks

@ispobock

[3/N] Achieve fault tolerance at the DP level

#11657 opened Oct 15, 2025 by ympcMark • Draft

4 tasks

check_offload_progress more frequently run-ci

#11656 opened Oct 15, 2025 by pansicheng

4 tasks

@hzh0425

[DeepseekV32] Enable flashmla_prefill kernel with fp8 kvcache

#11655 opened Oct 15, 2025 by hlu1 • Draft

4 tasks

Fuse writing KV buffer into rope kernel (amd gpu sgl-kernel)

#11654 opened Oct 15, 2025 by wejoncy

4 tasks

ProTip! Type g p on any issue or pull request to go back to the pull request listing page.

Navigation Menu

Search code, repositories, users, issues, pull requests...

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Pull requests: sgl-project/sglang

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Pull requests list