kvcache-ai/sglang
1
0
Fork 0
mirror of https://github.com/kvcache-ai/sglang.git synced 2026-07-10 17:27:14 +00:00
Code Issues Packages Projects Releases Wiki Activity
7,934 Commits 157 Branches 0 Tags
71cb90378b853d892f952f76b66cd48816daeca0
Commit Graph

5177 Commits

Author SHA1 Message Date
Even Zhou
71cb90378b [NPU] fix for NPU memory settings logic (#15258) 2025-12-16 17:04:22 -08:00
Trevor Morris
c8c64876a7 [NVIDIA] Fixes for NVFP4 all-gather with spec decoding (#15280) 2025-12-16 16:58:39 -08:00
Yineng Zhang
0861dca81f Revert "[misc] Upgrade cutedsl to 4.3.1 (#14857)" (#15293) 2025-12-16 16:31:32 -08:00
amysaq2023
ccc8f3b266 support non disturbing remote instance weight loader v2 (#14997) 
Signed-off-by: Anqi Shen <amy.saq@antgroup.com>
 2025-12-16 14:39:56 -08:00
Neal Vaidya
a4c762811a Remove incorrect BlockRemoved event emission during node splits (#14934) 
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
 2025-12-16 14:11:24 -08:00
Baizhou Zhang
28a19e494b Fix lint (#15281) 2025-12-16 13:36:01 -08:00
Baizhou Zhang
0261c4aff7 [misc] Upgrade cutedsl to 4.3.1 (#14857) 2025-12-16 12:11:56 -08:00
jacky.cheng
8ac350f335 [AMD] Support fused_rms_mxfp4_quant in the prefill stage for DeepSeek-R1-MXFP4 (#14975) 2025-12-16 12:03:58 -08:00
kk
99401e7b1a Fix accuracy issue when using a16w16 mla_decode_fwd (#14936) 2025-12-16 09:55:18 -08:00
Mick
f95729b06f [diffusion] doc: update profiling.md (#15270) 2025-12-16 23:48:32 +08:00
R0CKSTAR
9f4ed93dd8 [diffusion] multi-platform: use current_platform.device_type to replace hard-coded cuda device (#15232) 
Signed-off-by: Xiaodong Ye <yeahdongcn@gmail.com>
 2025-12-16 22:17:33 +08:00
Liangsheng Yin
ecb401ed42 Enhance runtime memory check in CI (#15192) 2025-12-16 21:40:38 +08:00
Ke Bao
b399e3ac4f Support piecewise cuda graph for fused marlin moe (#15100) 2025-12-16 20:05:32 +08:00
Kenny Yao
5e96beb3e5 Adding tool calling and reasoning parser support for Intern-S1 (#14866) 
Co-authored-by: KennyYao2001 <kennyy@andrew.cmu.edu>
Co-authored-by: Cursor AI <cursor@example.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Changyi Yang <112288487+ChangyiYang@users.noreply.github.com>
 2025-12-16 00:01:58 -08:00
haoyangli-amd
9327482baa [bugfix][quark] Fixed an issue where per_token could not be properly recognized when the token count was 1. (#14415) 2025-12-15 22:54:31 -08:00
Shangming Cai
36fcf71fff [Qwen3-next] Add PD disaggregation support for mamba with extra_buffer (#15180) 
Signed-off-by: Shangming Cai <csmthu@gmail.com>
Co-authored-by: ybyang <10629930+whybeyoung@users.noreply.github.com>
 2025-12-16 14:36:00 +08:00
Xiaoyu Zhang
6292d97135 [diffusion] fix: fix pack qkv opt break tensor parallel (#15225) 2025-12-16 14:33:49 +08:00
ゆり
3e4d431a44 [Feature] Add AIME25 dataset support for SGLang simple_eval (#14990) 
Co-authored-by: zkexorability <zkexorability@gmail.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
 2025-12-15 21:59:40 -08:00
Yibo Cai
22587bc0b4 [BugFix] Fix CPU inference failure (#15231) 2025-12-15 21:32:41 -08:00
Muqi Li
1da5cd638f [Bugfix][Tool Call] Add null system prompt to support tool system prompt (#15092) 
Signed-off-by: Muqi Li <muqi1029@gmail.com>
 2025-12-15 19:40:10 -08:00
XDaoHong
4733fcff1f [Feature] npu support enable_torch_compile for torchair backend (#13410) 
Co-authored-by: ZhengdQin <zhengdqin@gmail.com>
 2025-12-16 09:23:51 +08:00
Liwansi
30da2f0598 [NPU][eagle3] support qwen eagle3 on NPU (#14820) 2025-12-16 02:25:13 +08:00
Xiaoyu Zhang
4901693110 [diffusion] perf: support FFN pack gate and up proj for Z-Image(#15201) 
Co-authored-by: Mick <mickjagger19@icloud.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-12-16 01:18:47 +08:00
ratish
3d484be547 fix(attention): Prevent trtllm_mha auto-selection with eagle3 speculative decoding (#15127) 2025-12-15 16:42:26 +00:00
Xiaoyu Zhang
c0d94440b7 [diffusion] perf: support pack qkv for Z-Image (#15191) 2025-12-16 00:22:24 +08:00
Mick
1dedb63860 [diffusion] chore: minor code cleanups (#15190) 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-12-15 23:57:02 +08:00
Xiaoyu Zhang
7bc8b1532e [diffusion] fix: fix AttributeError in _build_parallelism_config when accessing tp_group.device_group (#15196) 
Co-authored-by: Mick <mickjagger19@icloud.com>
 2025-12-15 23:41:06 +08:00
roikoren755
9003a4369d Add missing assertion in NemotronH path (#15193) 
Signed-off-by: Roi Koren <roik@nvidia.com>
 2025-12-15 06:17:21 -08:00
Mick
b098b1ae24 [diffusion] fix: fix video model sp when resolution is not specified (#15047) 
Co-authored-by: Brain97 <Brain97@users.noreply.github.com>
 2025-12-15 20:25:43 +08:00
Lancer
abd3e048f2 [diffusion] fix: fix pytorch non-writable array warning (#15017) 2025-12-15 20:18:54 +08:00
Xiaoyu Zhang
92c29d43ac [diffusion] fix: cache dit with parallel (#15163) 
Co-authored-by: Mick <mickjagger19@icloud.com>
 2025-12-15 19:15:51 +08:00
DarkSharpness
f03bfa4ce3 [Feature] Fuse mrope all in 1 kernel (#14906) 2025-12-15 02:50:55 -08:00
kk
2ea844ec81 Fused two elementwise kernels for k_nope and k_pe concat (#14862) 
1 TC failure to check, but irrelevant to this code change
 2025-12-15 01:33:33 -08:00
blzheng
d16ff357db [CPU] Add Gemma3RMSNorm kernel in sgl-kernel and add ut (#9324) 2025-12-15 00:24:02 -08:00
Yuhao Yang
01b955ac3d [diffusion] model: support mutli-image input and qwen-image-edit-2509 (#15005) 2025-12-15 16:17:10 +08:00
mmdbhs
16e6bc20b0 fix CompressedTensorsW8A8Int8 min_capability (#13914) 
Co-authored-by: Fan Yin <1106310035@qq.com>
Co-authored-by: Peng Zhang <aniz1905@gmail.com>
 2025-12-15 15:50:39 +08:00
Liangsheng Yin
372507649d Tiny improve summary text in bench_one_batch_server.py (#15158) 2025-12-15 14:59:11 +08:00
Lianmin Zheng
702426b06a Fix import warnings (#15144) 2025-12-14 21:25:18 -08:00
Douglas Yang
9e9a61691e ci: adding errors to Github summary (#14778) 2025-12-14 21:08:16 -08:00
Yuan Luo
3912ee4991 [VLM] feat: support chunked vit attention (#14907) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2025-12-15 12:11:02 +08:00
b8zhong
1ab9b8e0a3 Enable TRT AllReduce Fusion by default (#14764) 
Co-authored-by: Brayden Zhong <b8zhong@users.noreply.github.com>
 2025-12-14 20:01:49 -08:00
Hanming Lu
e61dabf5e4 [Qwen3-next] support mamba radix cache for overlap scheduler (#14792) 2025-12-14 18:54:16 -08:00
Xiaoyu Zhang
4513f549ee [diffusion] fix: fix default resolution 720p width from 1080 to 1280 (#15058) 2025-12-15 09:16:47 +08:00
YAMY
c96903074c [NSA] Fix NSA backend assertion error when running DeepSeek-V3.2 PP with radix-cache (#15086) 2025-12-14 17:13:18 -08:00
Hudson Xing
99cb2ed988 [refactor] Move trtllm_fp8_kv_kernel to triton_ops directory (#15044) 2025-12-14 15:22:37 -08:00
danielafrimi
8102e36b5d Add NanoV3 reasoning parser support (#15113) 2025-12-14 12:09:44 -08:00
roikoren755
3f0482174a Fix Mamba2-based models' default attention backend (#15117) 
Signed-off-by: Roi Koren <roik@nvidia.com>
 2025-12-14 11:08:48 -08:00
Ziming Huang
997ea57eaf Fix tensor mismatch error in sepc + topk > 1 + page_size > 1 (#14874) 2025-12-15 01:10:58 +08:00
Xiaoyu Zhang
64b5c3ab90 [diffusion] refactor: refactor fuse qkv with QKVParallelLinear linear (#15090) 
Co-authored-by: Mick <mickjagger19@icloud.com>
 2025-12-15 00:33:29 +08:00
Tianyu Guo
9acb21ae27 feat: support EPD disaggregation (#12263) 
Co-authored-by: liusy58 <liusy58@linux.alibaba.com>
Co-authored-by: ZhengWG <zwg0606@gmail.com>
Co-authored-by: Nicholas <45984215+liusy58@users.noreply.github.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
Co-authored-by: Yuhao Yang <47235274+yhyang201@users.noreply.github.com>
 2025-12-14 22:30:08 +08:00