kvcache-ai/sglang
1
0
Fork 0
mirror of https://github.com/kvcache-ai/sglang.git synced 2026-07-08 16:27:09 +00:00
Code Issues Packages Projects Releases Wiki Activity
8,134 Commits 157 Branches 0 Tags
fa2966983a04584f381a4d144c97a9e595eb0ac1
Commit Graph

5312 Commits

Author SHA1 Message Date
Tianyu Guo
fa2966983a Support PP for zmq_to_scheduler (#15312) 2025-12-23 17:07:55 +08:00
Douglas Yang
f9dd90ac35 fix: increasing H200 test timeout (#15600) 2025-12-23 01:00:37 -08:00
Alison Shao
ac42797cf7 [CI] Enable retry logic for flaky CI tests (#14983) 2025-12-22 22:23:42 -08:00
Alison Shao
989d4b3012 [CI] Migrate nightly tests to test/registered/ (#15582) 2025-12-22 22:16:32 -08:00
Baidu-AIAK
bc3ca30023 [PD] Support fake decode for PD disaggregation without prefill node (#14628) 
Co-authored-by: sunhailiang <sunhailiang@baidu.com>
 2025-12-23 12:43:33 +08:00
yuchengz816-bot
061f41affc MoE: Skip SiLU/GELU activation for masked experts (#15539) 
Co-authored-by: Runkai Tao <rt572@physics.rutgers.edu>
 2025-12-22 19:08:31 -08:00
Yuxuan Zhang
82f1d6157f [GLM-ASR] GLM-ASR Support (#15570) 
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
 2025-12-22 17:37:55 -08:00
Lianmin Zheng
5e1a495c65 Improve engine customization interface (#15635) 2025-12-22 14:24:16 -08:00
sglang-bot
34013d9d5a chore: bump sgl-kernel version to 0.3.20 (#15590) 
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
 2025-12-22 12:32:34 -08:00
SeanWeiSean
7759716786 bugfix[schedule]: Refactor sort method and add related UT (#13576) 
Co-authored-by: Yuxuan Wei <w1300012920@pku.edu.cn>
Co-authored-by: Yuxuan Wei <w1300012920@gmail.com>
Co-authored-by: Yuxuan Wei🚚 <yuxwei@microsoft.com>
 2025-12-23 03:13:57 +08:00
Liangsheng Yin
3c882db3ad Adjust wrong mtp meaning introduce by mimo (#15632) 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-12-23 02:06:46 +08:00
Xiaoyu Zhang
d77f3fccbf [Diffusion] Support peak memory record in offline generate and serving (#15610) 2025-12-22 21:21:21 +08:00
Yuan Luo
828dec1c7c [VLM] Tiny: Unify VLM environment variables (#15572) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2025-12-22 17:32:37 +08:00
ryang
575a49dc0e [diffusion] chore: remove default post-denoising dit offload in local mode (#15573) 2025-12-22 17:01:35 +08:00
fzyzcjy
e62e17442e Tiny enable soft watchdog in CI for stuck without logs (#15616) 2025-12-22 17:01:04 +08:00
fzyzcjy
d5431ff894 Tiny add stuck simulation (#15613) 2025-12-22 17:00:18 +08:00
fzyzcjy
454a2544f2 Support soft watchdog for tokenizer/detokenizer/dp-controller processes (#15607) 2025-12-22 16:59:16 +08:00
fzyzcjy
89619a9904 Tiny avoid EnvField misuse (#15612) 2025-12-22 16:20:47 +08:00
Hexq0210
cb30d056e3 add decode round robin policy (#15164) 2025-12-22 14:48:52 +08:00
Liangsheng Yin
beae3f961c Adapt fixture-kit to gsm8k mixin (#15599) 2025-12-22 14:19:35 +08:00
fzyzcjy
ad7f35fb9d Support gsp send routing id in bench serving (#15588) 2025-12-22 11:32:24 +08:00
fzyzcjy
f4100732b8 Tiny fix bench serving GSP mode cache file strategy (#15587) 2025-12-22 11:27:55 +08:00
Baizhou Zhang
468931b572 [Tiny]Move deepseek fp4 cutlass moe test to per-commit test (#15565) 2025-12-21 18:08:07 -08:00
FlyPanda
a3a552232d [feature] support hicache-3fs usrbio lib build for ubuntu24.04 (#15230) 2025-12-21 17:00:38 -08:00
Chenxi Li
0bf95e6d69 Fix type mismatch in LoRA batch validation causing assertion failures (#15427) 2025-12-21 15:54:41 -08:00
Qiaolin Yu
254de6d2fd Add triton_fused_moe config for GLM-4.6-FP8 tp8 blackwell (#15569) 2025-12-21 13:41:22 -08:00
Jincong Chen
350fbbf4dc fix ds3.2 nsa backend prefill TBO (#14901) 2025-12-21 13:16:46 -08:00
Liangsheng Yin
393e2f9b62 Revert "[FusedMoE] Fix fused w13 tp sharded weight loading" (#15579) 2025-12-22 04:15:24 +08:00
Liangsheng Yin
8766a1dd24 [1 / N] Clean up logprob utils (#15509) 2025-12-22 03:12:25 +08:00
Junrong Lin
bed301a5ac [Feature] Enable return routed experts (#12162) 
Co-authored-by: yizhang2077 <1109276519@qq.com>
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
 2025-12-21 15:16:43 +08:00
Ke Bao
8fe3e37468 Support piecewise cuda graph for dsv3 fp4 (#15531) 2025-12-21 14:50:32 +08:00
YAMY
6014365564 [EAGLE] Fix slow Triton compilation in EAGLE KV cache copy by chunking large num_locs_upper (#15111) 2025-12-21 14:14:14 +08:00
Yinghai Lu
fc05acc2c7 [FusedMoE] Fix fused w13 tp sharded weight loading (#15432) 2025-12-21 13:59:36 +08:00
Mick
1ed946680a [diffusion] bench: improve bench_serving by adding more controlling args (#15554) 2025-12-21 13:37:45 +08:00
Mick
d7fbe73bf2 [diffusion] chore: minor improvements and typo-fixing (#15556) 2025-12-21 13:37:10 +08:00
Xiaoyu Zhang
42bff706df [diffusion] profiling: simplify --perf-dump-path JSON output (remove duplicate denoise steps) (#15537) 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-12-21 12:56:46 +08:00
Xiaoyu Zhang
4b351f6b95 Apply new moe align block size kernel (#14134) 2025-12-21 10:13:32 +08:00
Yuan Luo
050f108c29 Optimize Bailing-MoE with FlashInfer Fused All-Reduce (#15526) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2025-12-20 17:34:04 -08:00
Xinyuan Tong
0a346d3bd9 feat: Add limit-mm-data-per-request argument to server arguments (#15418) 
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
 2025-12-20 10:44:47 -08:00
Mick
bc18cb8631 [diffusion] refactor: change zmq socket type to router for scheduler (#15479) 2025-12-21 00:39:54 +08:00
Xiaoyu Zhang
bee8ac5b88 [diffusion] doc: add --perf-dump-path section to profiling doc (#15533) 2025-12-21 00:15:27 +08:00
Mick
41bd76e18b [diffusion] log: fix wrong use of suppress_other_loggers (#15534) 2025-12-20 23:43:55 +08:00
Mick
c6ca1b3afc [diffusion] chore: allow all attention backends if not specified (#15530) 2025-12-20 23:14:55 +08:00
Xiaoyu Zhang
8999ce754f [diffusion] perf: support zero-cost weight offload and overlap with compute for wan-series (#15511) 2025-12-20 22:52:40 +08:00
Yuan Luo
019517a356 [VLM] Support ViT Piecewise CUDA Graph for Qwen3-VL (#15320) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2025-12-20 21:00:07 +08:00
mlmz
1f1f05a85e vlm: refactor engine vlm params and support processor output as input (#14091) 
Co-authored-by: Mick <mickjagger19@icloud.com>
Co-authored-by: zhaochenyang20 <zhaochenyang20@gmail.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: BenYao21 <cyao22@asu.edu>
Co-authored-by: minleminzui <minleminzui@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: 赵晨阳 <zhaochen20@outlook.com>
 2025-12-20 18:31:24 +08:00
Yuan Luo
165f5c04cb Optimize MiMo-V2-Flash by flashinfer fused allreduce (#15464) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2025-12-20 17:45:18 +08:00
Артем Савкин
3e01f3a533 [NPU] [BUGFIX] [CRITICAL!] Fix NPU inference (torch_npu._npu_reshape_and_cache() crash) (#15484) 2025-12-20 14:53:46 +08:00
yctseng0211
6468cb5823 [AMD] remove the redundant projection (#15178) 2025-12-19 22:10:46 -08:00
Qiaolin Yu
e220da1723 tiny fix sampling seed for completion api (#15498) 2025-12-19 20:32:13 -08:00