Commit Graph

9885 Commits

Author SHA1 Message Date
Simo Lin
8ab5d8b40d [model-gateway] add qwen2.5_vl model image processor (#14375) 2025-12-03 12:51:30 -08:00
Simo Lin
03575ce38d [model-gateway] add qwen2_vl model image processor and tests (#14374) 2025-12-03 12:34:06 -08:00
alisonshao
80518bea65 Fix validation to detect missing model files before loading (#14253) 2025-12-03 11:36:07 -08:00
Baizhou Zhang
7e78825d5a [Tiny]Small fixes in deepseek v32 doc (#14372)
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
2025-12-03 11:35:40 -08:00
sunxxuns
5bbd83a2c8 ci: Migrate AMD workflows to new MI325 runners; temporarily disabled failed CI's to be added back (#14226) 2025-12-03 11:33:27 -08:00
Simo Lin
abf6272bdd [model-gateway] add llava model image processor and tests (#14371) 2025-12-03 11:18:00 -08:00
Lianmin Zheng
46d7b35ec7 Move custom_ops under layers; move _custom_ops.py → custom_all_reduce_ops.py (#14326) 2025-12-03 10:33:37 -08:00
Sulfur6-L8972
20aad5b5ab Single Batch Overlap for MoE Models (#9660)
Co-authored-by: Cheng Wan <wan4ch@gmail.com>
Co-authored-by: Zqy11 <841971412@qq.com>
Co-authored-by: AniZpZ <aniz1905@gmail.com>
Co-authored-by: TianyuZhang1214 <tianyuzhang1214@gmail.com>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
2025-12-03 10:07:42 -08:00
blzheng
974c562a25 [CPU] add fused_qkvzba_split_reshape_cat kernel for Qwen3-next (#12330) 2025-12-03 23:46:08 +08:00
Dongjie Zou
aca0d01d3f [diffusion] doc: add vae path to cli doc#14004 (#14355)
Co-authored-by: BBuf <1182563586@qq.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
2025-12-03 15:13:25 +00:00
VDV1985
dc1635023f [NPU][Doc] updated installation guide for Ascend NPU (#13585)
Co-authored-by: Howeee <15935120809@163.com>
Co-authored-by: ronnie_zheng <zl19940307@163.com>
2025-12-03 16:58:49 +03:00
Liangsheng Yin
24903b88ba Tiny adjust CI testcases (#14362) 2025-12-03 21:19:51 +08:00
Michelle Wu
443d7bcd83 [Ascend] fix AscendAttnMaskBuilder bug to support float16 models (#14271) 2025-12-03 19:37:16 +08:00
chenxu140
16d8de2284 [bugfix] NpuFuseEPMoE miss initialization parameters (#14295) 2025-12-03 19:36:41 +08:00
ZhengdQin
d122e32467 [NPU] bug fix: w_vc need contiguous for NPU batch_matmul_transpose ops (#13980) 2025-12-03 19:35:18 +08:00
Cheng Wan
96cc10834a [CI] update estimated elapsed time of some unittests (#14347) 2025-12-03 01:21:40 -08:00
Yuhao Yao
77512ae0d7 [bugfix] Fix prefill tbo disabled when --deepep-mode=auto (#14333)
Co-authored-by: Cheng Wan <wan4ch@gmail.com>
2025-12-03 01:20:33 -08:00
Xuan Liao
c233e9d7a9 [CPU] Support chunk_gated_delta_rule kernel for Qwen3-Next (#12441) 2025-12-03 17:03:48 +08:00
Simo Lin
58ac3f317b [model-gateway] add image processor and transformer structure (#14344) 2025-12-03 00:04:06 -08:00
Shangming Cai
93452a8252 [PD] Support decode pp for PD disaggregation (#14265)
Signed-off-by: Shangming Cai <csmthu@gmail.com>
2025-12-03 14:35:29 +08:00
b8zhong
65c8568c4a sync attention, deepseek doc (#14335)
Co-authored-by: Brayden Zhong <b8zhong@users.noreply.github.com>
2025-12-02 21:19:40 -08:00
Baizhou Zhang
4bcc5879af [Doc] Fix DeepSeek V32 Doc (#14336) 2025-12-02 21:06:55 -08:00
Simo Lin
d5ea8c7176 [model-gateway] multimodality initialization (#13350) 2025-12-02 19:41:40 -08:00
Vikram
42271376d1 [bug fix] use npu phy id in container env (#14266)
Co-authored-by: jinke15 <jinke15@jd.com>
2025-12-03 11:33:43 +08:00
Mick
84e0abb7b1 Update CODEOWNERS for multimodal (#14329) 2025-12-03 11:04:40 +08:00
Johnsonms
043f13171f [Performance] Optimize NSA Indexer K/S Buffer Access with Fused Triton Kernels (#13812)
Co-authored-by: Johnsonms <johnson@together.ai>
2025-12-02 18:53:06 -08:00
Dongjie Zou
f764c6910d [diffusion] feat: support distilled vae generic (#14195)
Co-authored-by: BBuf <1182563586@qq.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
2025-12-03 10:27:31 +08:00
Baizhou Zhang
922054079c [Doc] Update DeepSeek-V3.2 document (#14321) 2025-12-02 18:19:39 -08:00
Even Zhou
7d1a130cde Refactor custom allreduce logics (#13710)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Kangyan-Zhou <zky314343421@gmail.com>
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
2025-12-02 17:20:05 -08:00
sglang-bot
7ae368efde chore: bump SGLang version to 0.5.6 (#14316)
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
2025-12-02 17:17:13 -08:00
sunxxuns
c4e20caded ci: Add zyzshishui to CI permissions (#14324)
Co-authored-by: root <root@mi300x8-005.atl1.do.cpe.ice.amd.com>
2025-12-02 17:00:31 -08:00
Simo Lin
5dad1ff1b6 [model-gateway] add workflow for external model providers (#14323) 2025-12-02 16:47:06 -08:00
Lianmin Zheng
ca52ed425f Clean up imports and move files (#14317) 2025-12-02 16:31:54 -08:00
Douglas Yang
5c03aa3e9d Adding section for scheduled PR test runs on main (#14309) 2025-12-02 14:52:44 -08:00
Douglas Yang
253be18e52 Fix nonetype error for ci failure monitor (#14319) 2025-12-02 14:24:25 -08:00
alisonshao
084b06e79d Add /rerun-stage slash command to rerun specific PR test stages (#14262) 2025-12-02 14:23:38 -08:00
Lianmin Zheng
fc6fb550ec [Minor] update docs on CI (#14315) 2025-12-02 12:06:54 -08:00
Eva20150932-atlascloud
7c38eca1e4 feat: DeepSeek new v3.2 encoding (#14249)
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
2025-12-02 11:41:05 -08:00
Quanfeng Li
427b08e24d Init TBO with dp_padded batch (#11423)
Co-authored-by: Cheng Wan <wan4ch@gmail.com>
Co-authored-by: Yuhao Yao <37280700+yuhyao@users.noreply.github.com>
2025-12-02 10:34:26 -08:00
alisonshao
0141ca370f Revert PR #14044: Restore separate memory pool for piecewise CUDA graph (#14278) 2025-12-02 09:53:16 -08:00
alisonshao
25a6be4930 Fix duplicate download log messages in multi-process environment (#14299) 2025-12-02 09:33:18 -08:00
Antonin Vidon
df1f31241b [sgl-kernel] fix runtime error while preloading CUDA runtime (#13089) 2025-12-02 23:03:51 +08:00
Xiaoyu Zhang
c5947ecd85 Opt moe align block size kernel (#14133) 2025-12-02 19:13:55 +08:00
Mick
9530b76630 [diffusion] refactor: simplify DmdDenoisingStage (#14269) 2025-12-02 18:59:40 +08:00
Jinyan Chen
3067b3f050 [diffusion] chore: improve model info registration and searching strategy (#14281)
Co-authored-by: Jinyan Chen <jinyanc@nvidia.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
2025-12-02 18:28:59 +08:00
alisonshao
e0ec42c710 [CI] Fix 4-GPU test timeout by using 3 partitions (#14287) 2025-12-02 16:47:26 +08:00
Mick
9c9d7091cb Update CODEOWNERS for multimodal_gen (#14286) 2025-12-02 16:15:19 +08:00
Simo Lin
51a86ce69e [model-gateway] change rust package name to sgl-model-gateway instead (#14283) 2025-12-02 00:06:54 -08:00
Lianmin Zheng
64092c8b55 [Auto Sync] Rename is_hybrid to is_hybrid_swa (#14252)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Hanming Lu <69857889+hanming-lu@users.noreply.github.com>
Co-authored-by: Hanming Lu <hanming@x.ai>
2025-12-01 23:24:24 -08:00
sglang-bot
63b9300f00 chore: bump sgl-kernel version to 0.3.18.post2 (#14244) 2025-12-01 23:14:12 -08:00