EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity
6,122 Commits 8 Branches 0 Tags
704160017dbcdc173c08ef23723fd70de9133aee
Commit Graph

4096 Commits

Author SHA1 Message Date
Yineng Zhang
704160017d fix: resolve flashinfer 0.4.1 import (#11940) 2025-10-21 17:19:57 -07:00
Yineng Zhang
c461e7714d [Auto Sync] Update forward_batch_info.py (20251021) (#11934) 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: yinghui <32845984+cicirori@users.noreply.github.com>
 2025-10-21 15:52:15 -07:00
Zheng Wengang
fde2decf8b [BugFix][Qwen3-VL]: add metadata for video in qwen3-vl (#11377) 2025-10-21 15:36:01 -07:00
Yineng Zhang
9792b9d7e3 chore: upgrade flashinfer 0.4.1 (#11933) 2025-10-21 14:46:31 -07:00
Baizhou Zhang
ef4a8097b8 Rename flashmla kernel options of nsa backend for better readability (#11876) 2025-10-21 13:14:16 -07:00
Baizhou Zhang
ebff4ee648 Update sgl-kernel and remove fast hadamard depedency (#11844) 2025-10-21 13:13:54 -07:00
Serge Panev
2b1da821b5 [NVIDIA] Add new SMs support for Spark & Thor (#11287) 
Signed-off-by: Serge Panev <spanev@nvidia.com>
 2025-10-22 02:02:24 +08:00
Liangsheng Yin
97710ccd1a Fix flush cache API for spec v2 (#11918) 2025-10-21 23:01:16 +08:00
Kai-Hsun Chen
c61b0b294c [quantization][MoE] fix the check for tp_size / moe_ep_size / moe_intermediate_size / weight_block_size_n (#11702) 
Signed-off-by: Kai-Hsun Chen <khchen@x.ai>
 2025-10-21 21:25:28 +08:00
Vincent Zhong
e8640ee9be [smol] [perf] Inverse perm improvement (#11482) 
Signed-off-by: vincentzed <207368749+vincentzed@users.noreply.github.com>
 2025-10-21 19:18:10 +08:00
b8zhong
d0a64c7e2c vlm: enforce pybase64 for image and str encode/decode (#10700) 2025-10-21 19:05:32 +08:00
Zhengke Zhou
260fe755b6 Simplify multi-tokenizer (#11295) 
Signed-off-by: zhengkezhou1 <madzhou1@gmail.com>
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
 2025-10-21 16:33:29 +08:00
ybyang
dbb16bedd5 Support Thinking Budget (via custom_logit_processor for OpenAI API) [Fix #6572] (#11416) 
Signed-off-by: ybyang <ybyang7@iflytek.com>
Co-authored-by: YorkSu <york_su@qq.com>
 2025-10-21 16:27:56 +08:00
Neelabh Sinha
852c0578fd [FEATURE] Add OpenAI-Compatible LoRA Adapter Selection (#11570) 2025-10-21 15:44:33 +08:00
Atream
7e6191c098 init support for KTransformers Heterogeneous Computing (#11487) 
Co-authored-by: Jianwei Dong <1913953267@qq.com>
 2025-10-21 00:17:02 -07:00
Gaurav Verma
6f9b66bdda [AMD] Update wave-lang to 3.8.0 (#11878) 
Signed-off-by: xintin <gaurav.verma@amd.com>
 2025-10-20 23:11:09 -07:00
Qiaolin Yu
d9a20fd28a Use trtllm_mla decode kernel for draft extend in speculative decoding (#11664) 2025-10-21 11:42:09 +08:00
Meng, Hengyu
b113c72e7a Init attention backend for Intel XPU (#10656) 
Co-authored-by: guangyey <guangye.yu@intel.com>
Co-authored-by: DiweiSun <105627594+DiweiSun@users.noreply.github.com>
 2025-10-21 11:41:28 +08:00
zhangdonghao-zdh
fb6cc7b000 Fix RotaryEmbedding for fp32 input (#11843) 2025-10-21 10:56:48 +08:00
Xiaoyu Zhang
8374a96e49 piecewise cuda graph support qwen3-moe (#11845) 2025-10-21 10:55:49 +08:00
Yuan Luo
74de76c685 Revise MRotaryEmbedding's forward (#11859) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
Co-authored-by: 羽癫 <yudian.zy@antgroup.com>
Co-authored-by: b8zhong <b8zhong@uwaterloo.ca>
 2025-10-21 10:38:29 +08:00
Chang Su
9c0b1eb5ad [router][grpc] Fix wram-up random token ids for small models (#11887) 2025-10-20 19:22:17 -07:00
Lianmin Zheng
01f14a7ad2 [code move] move pp into a separate mixin (#11838) 2025-10-20 18:46:56 -07:00
Lianmin Zheng
43ad05907c [Auto Sync] Update scheduler.py, server_args.py (20251020) (#11875) 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Kan Wu <wukanustc@gmail.com>
 2025-10-20 17:41:19 -07:00
fzyzcjy
0917c5da8c Support mixing cutedsl and deepgemm backend (#11807) 2025-10-21 07:38:35 +08:00
penguin_wwy
184a4df697 Replace function call with set literal (#11867) 2025-10-21 01:39:16 +08:00
Qiaolin Yu
f7b1d8c5ab Fix acc len and gen throughput metrics when enabling overlap-spec (#11823) 
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
 2025-10-21 01:34:38 +08:00
Cheng Wan
bfc3b3f786 [9/N] MoE Refactor: cleanup dispatcher interfaces (#11847) 2025-10-20 10:11:46 -07:00
Liangsheng Yin
da5bde4d16 Tiny fix main lint (#11862) 2025-10-20 19:57:24 +08:00
DarkSharpness
276e7b3e4e [Feature] New structural tag support (#10691) 2025-10-20 18:25:58 +08:00
ishandhanani
296f689242 fix(server_args): handle tokenizer init conflicts (#11776) 2025-10-20 00:27:19 -07:00
Shane A
d383e6616e [Model] Add Olmo 3 model support (#11396) 2025-10-19 23:59:16 -07:00
Shangming Cai
a2ba0bc3df Tiny clean up for PD module and doc (#11747) 
Signed-off-by: Shangming Cai <csmthu@gmail.com>
 2025-10-20 11:52:42 +08:00
Ziming Huang
6d2d0ce285 [PD] Improve eagle acceptance rate by transferring draft model hidden states (#10801) 
Co-authored-by: Shangming Cai <csmthu@gmail.com>
 2025-10-20 11:52:18 +08:00
Yuan Luo
271d3d0d50 Support mrope triton kernel and add unit test (#11722) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
Co-authored-by: b8zhong <b8zhong@uwaterloo.ca>
 2025-10-20 11:51:07 +08:00
ykcombat
c4e81e64fb [Feature] Use current greenctx stream to communicate in PD-Multiplexing. (#11594) 2025-10-20 10:58:20 +08:00
harrisonlimh
c726d44cc7 Recapture cuda graph after model weight update to resolve IMA error (#11780) 2025-10-20 10:50:03 +08:00
huangtingwei
cae3956585 check master server for mooncake store (#10510) 2025-10-20 09:37:09 +08:00
Liu-congo
be0058bc05 [BugFix] replace the input_to_float8 used in dsv2 (#11612) 
Signed-off-by: Liu-congo <1502632128@qq.com>
 2025-10-19 19:34:13 -05:00
fzyzcjy
a8ba32798e Fix triton_kernels import error on some hardwares (#11831) 2025-10-20 08:14:47 +08:00
Johnny
252dc4e112 [NVIDIA] FA3/FA4 Fix (#11606) 
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
 2025-10-19 17:10:10 -07:00
Baizhou Zhang
cbb5fc2edc [CI] Add CI test for DeepSeek V3.2 MTP (#11835) 2025-10-19 17:00:25 -07:00
Stefan He
4fff1ec1d9 Deterministic Mode: Add 1-stage triton kernel for prefill (#11147) 
Co-authored-by: Minglei Zhu <mingleizhu1122@gmail.com>
Co-authored-by: Binyao Jiang <bijiang@linkedin.com>
 2025-10-20 01:47:36 +08:00
Liangsheng Yin
7a020e0f3b [Test] Add basic matched stop for beta eagle (#11833) 2025-10-20 01:17:00 +08:00
Liangsheng Yin
48738af7f9 [CI] always print back trace in retry() (#11834) 2025-10-20 01:12:49 +08:00
Paiiii
efa473348b [Spec Decoding] Support MTP for dsv3.2 (#11652) 
Co-authored-by: Paiiiiiiiiiiiiii <zengpai@baidu.com>
 2025-10-19 23:44:22 +08:00
Liangsheng Yin
d658f0497e [overlap-spec] fix stop condition and trimming (#11819) 2025-10-19 22:00:20 +08:00
Liangsheng Yin
57e25de756 Revert "Fix: Dynamic RoPE Cache Expansion to Prevent Position-ID Out-of-Bounds in EAGLE + Long-Sequence Workloads" (#11827) 2025-10-19 19:44:06 +08:00
fzyzcjy
12eb02e982 Change bf16 to fp8 for some gemms in attention for DeepSeek ckpt v2 (#11805) 2025-10-19 16:15:13 +08:00
fzyzcjy
002d037359 Avoid generation gets hanging when user specifies multiple event loops (#5162) 
Co-authored-by: Yineng Zhang <me@zhyncs.com>
 2025-10-19 16:12:49 +08:00