Pull requests: sgl-project/sglang

Pull requests list

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

#11707 opened Oct 16, 2025 by FlamingoPg

1 of 4 tasks

@FlamingoPg @zhyncs

[NVIDIA] Update to leverage flashinfer trtllm FP4 MOE throughput kernel high priority run-ci

#11563 opened Oct 13, 2025 by jiahanc

4 tasks done

@ispobock @zhyncs @Qiaolin-Yu

[Do not merge] Adding flashinfer_cubin high priority run-ci

#11459 opened Oct 11, 2025 by Fridge003

4 tasks

@zhyncs

[Docs] update sgl-kernel readme run-ci

#11379 opened Oct 9, 2025 by FlamingoPg

1 of 4 tasks

@FlamingoPg @zhyncs

[Feature] Qwen3-Next & FLA: Support MTP topk>1; Up to 1.7% faster high priority run-ci

#11133 opened Oct 1, 2025 by byjiang1996

4 tasks done

@hebiao064 @byjiang1996 @yizhang2077 @zhyncs

Support profiling by stage high priority

#11110 opened Sep 30, 2025 by lpc0220

@zhyncs

model: qwen3-omni (thinker-only) high priority run-ci

#10911 opened Sep 25, 2025 by mickqian

4 tasks

@mickqian @zhyncs @JustinTong0323

[Feature] Accelerate Simple-EAGLE with a Fused Verify-Draft CUDA Graph high priority run-ci

#10866 opened Sep 24, 2025 by zhanxxxxxxx

4 tasks

@LorrinWWW @zhyncs

[6/n]decouple quantization implementation from vLLM dependency ready-to-merge run-ci

#10750 opened Sep 22, 2025 by Hongbosherlock

4 tasks

@AniZpZ @Hongbosherlock @FlamingoPg @zhyncs

[benchmark] refactor bench (part 1) high priority run-ci

#10409 opened Sep 13, 2025 by XucSh

4 tasks

@zhyncs

Add support for bf16 x bf16 cutlass fused MoE high priority run-ci

#10275 opened Sep 10, 2025 by nvcastet

4 tasks

@yuan-luo @hebiao064 @yizhang2077 @zhyncs @ch-wan

[WIP] Add checker of supported features for attention backends high priority

#10200 opened Sep 9, 2025 by Fridge003 • Draft

4 tasks

@zhyncs

feat: Add FP4 (E2M1) KV Cache Support with Quantization Utilities for MLA high priority quant run-ci

#10078 opened Sep 5, 2025 by JackChuang

4 tasks done

@AniZpZ @zhyncs @Fridge003

[Fix] Enhance flush_cache in PD disaggregation high priority run-ci

#9865 opened Sep 1, 2025 by duzeyan

1 of 4 tasks

@zhyncs

[Interface] Add an alias for sglang launch server high priority

#9800 opened Aug 29, 2025 by vincentzed

4 tasks

@zhyncs

update sgl-kernel for w4afp8_machete high priority run-ci

#9736 opened Aug 28, 2025 by mianpeng

@FlamingoPg @HydraQYH @zhyncs

Support modelopt llama4 nvfp4 workflow and fix issues high priority

#9526 opened Aug 23, 2025 by Edwardf0t1

1 of 4 tasks

@Alcanderian @zhyncs

[NVIDIA] adding DSR1 deployment guide on B200

#9408 opened Aug 20, 2025 by kushanam

4 tasks

@zhyncs

[POC] Overlap scheduler refactor with SD enhancement high priority run-ci speculative-decoding

#9334 opened Aug 19, 2025 by hnyls2002

@ispobock @zhyncs @Fridge003 @hnyls2002 @JustinTong0323

Optimize alloc_decode performance high priority

#8967 opened Aug 8, 2025 by fzyzcjy

6 tasks

@zhyncs

Elastic EP Support (Milestone 1 & 2) high priority

#8961 opened Aug 8, 2025 by UNIDY2002 • Draft

6 tasks

@fzyzcjy @zhyncs @ch-wan

[CI] Defer Resource-Intensive Tests to Scheduled Runs(Nightly and Weekly) ci enhancement

#8873 opened Aug 6, 2025 by key4ng

6 tasks

@slin1237 @zhyncs

Fix positional argument high priority

#8792 opened Aug 5, 2025 by liquanfeng

6 tasks done

@whybeyoung @zhyncs @ch-wan

[2/N]Support DeepSeek-R1 w4a8 low latency deepep high priority

#8464 opened Jul 28, 2025 by ayrnb

6 tasks

@zhyncs @ch-wan

fix: fix mtp use flashmla backend bugs

#7710 opened Jul 2, 2025 by zhangxiaolei123456

6 tasks

@yizhang2077 @ispobock @zhyncs @sleepcoo

ProTip! Mix and match filters to narrow down what you’re looking for.

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