Commit Graph

8713 Commits

Author SHA1 Message Date
Mohammad Miadh Angkad
05ab110e02 [Performance] Force split_k=1 for MXFP4 Triton kernels on Hopper (#16014)
Signed-off-by: Mohammad Miadh Angkad <MAngkad.BSDSBA2027@aim.edu>
2026-01-08 23:52:22 +08:00
Simo Lin
c8dc4d2d1f [smg][ci] migrate enable_thinking tests to new infrastructure (#16739) 2026-01-08 06:57:45 -08:00
cheng peng
82a8d77bc0 [Diffusion] model: fix zimage tp (#16719)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-01-08 22:47:21 +08:00
Xiaoyu Zhang
294ff71d18 [Diffusion] Avoid cpu2gpu sync in flashinfer rope and apply flashinfer rope to wanvideo (#16668)
Co-authored-by: Mick <mickjagger19@icloud.com>
2026-01-08 22:44:38 +08:00
Simo Lin
f52ae586b6 Remove migrated e2e_grpc/basic tests (#16738) 2026-01-08 06:30:45 -08:00
Simo Lin
2f8a36347c [smg][ci] migrate chat completions tests to new infrastructure and build wheel once and share via artifact (#16709) 2026-01-08 06:29:23 -08:00
fzyzcjy
b6e8a0d851 Add file size hints in bitwise model file verifier (#16735) 2026-01-08 22:28:52 +08:00
luoyuyan
fb7609f1dd Fix FP8 MoE NaN with DeepGEMM on Blackwell (#16622) 2026-01-08 22:24:12 +08:00
yuhao
d2ea44f775 VLM: enhance VL embedding model with video input support and revise warm-up strategy (#16635)
Co-authored-by: Mick <mickjagger19@icloud.com>
2026-01-08 22:12:01 +08:00
Hexq0210
20ca2c6e1e [NPU] update model and features supported (#16733) 2026-01-08 21:50:42 +08:00
fzyzcjy
83abecd0c2 Support pre-generating and using expected checksums (#16730) 2026-01-08 20:26:13 +08:00
fzyzcjy
d54f0a10b4 Support bitwise weight checksum verifier (#16729) 2026-01-08 20:19:25 +08:00
Lianmin Zheng
fb04e7e3c8 [Auto Sync] Update schedule_batch.py, common.py, eagle_info... (20260105) (#16519)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: cctry <shiyang@x.ai>
2026-01-08 02:35:46 -08:00
Douglas Yang
1e5de05e35 fix: adding timeout for install dependencies (#16706) 2026-01-08 00:30:41 -08:00
chenxu214
7dd679cbb9 [NPU][Bugfix] Fix qwen3 error when enable-dp-lm-head (#16115) 2026-01-08 15:15:43 +08:00
YC Tseng
3d51ae18a1 [AMD] Turn on AMD CI if rocm.Dockerfile changed (#16634) 2026-01-07 22:51:53 -08:00
Bingxu Chen
f9c0426692 [AMD CI] re-enable testcases missed when migrating ci test files (#16535)
Co-authored-by: michael-amd <michael.zhang@amd.com>
Co-authored-by: yctseng0211 <yctseng@amd.com>
2026-01-07 22:43:48 -08:00
陈一涵
48b8dcd42e [jit kernel] support dtype as a cpp template parameter (#16452) 2026-01-08 13:54:33 +08:00
Fan Lin
41b434a7e6 [diffusion] endpoint: add API endpoint to query loaded LoRA adapters information (#16533) 2026-01-08 13:51:26 +08:00
Hubert Lu
4935344fcd [AMD] Fix aiter page-size handling, DeepSeek MLA tuple inputs, and HiCache/FA3 decode-backend override (#16531) 2026-01-07 21:14:32 -08:00
Alison Shao
63cc97f4ef ci: migrate 2-GPU tests to test/registered/ (#16529) 2026-01-07 20:28:16 -08:00
Alan Kao
ab7d5829cd [AMD] Add pip install / wheel build support for ROCm sgl-kernel (#15627) 2026-01-07 20:18:29 -08:00
hw-csong
261860e17b [NPU][Bugfix] move free_page logics to cpu (#16608) 2026-01-08 12:00:18 +08:00
Yuwei An
154740bd4d Disable PCG TP Unittest (#16693)
Signed-off-by: Oasis-Git <ayw.sirius19@gmail.com>
2026-01-07 19:59:47 -08:00
MarcoDWei
1c09cbe3ed [Build] Enable full kernel in aarch64 wheel (#16155) 2026-01-07 19:40:03 -08:00
Yuhao Yang
e14f5ec8a8 [diffusion] refactor: eliminate redundant parameters in req (#16505)
Co-authored-by: Mick <mickjagger19@icloud.com>
2026-01-08 11:14:03 +08:00
Liangsheng Yin
8867d24879 Tiny adjust cancel PR workflow. (#16697) 2026-01-08 11:13:46 +08:00
siyu
6b3f93c4dd vlm: support SGLANG_MM_SKIP_COMPUTE_HASH for bypassing multimodal feature hashing (#16555) 2026-01-08 11:10:00 +08:00
Xiaoyu Zhang
5a5cece561 [Diffusion] clean useless and buggy set_seq_parallel_pg in yunchang (#16669) 2026-01-08 11:08:34 +08:00
Teng Ma
d566739b65 Add sufeng-buaa into CI_PERMISSION (#16625)
Signed-off-by: Teng Ma <teng-ma@linux.alibaba.com>
2026-01-08 11:01:32 +08:00
Simo Lin
4c46ecde80 [smg][ci] delete old responses api ci (#16695) 2026-01-07 18:24:12 -08:00
hlu1
12a0292bfd Revert "[sgl-kernel] Update flashmla to include fp8 sparse_mla optimizations" (#16678) 2026-01-08 10:23:06 +08:00
Simo Lin
a08dc5aa10 [smg][ci] rename 3rd models from cloud backend and delete dead code (#16692) 2026-01-07 18:19:44 -08:00
Junrong Lin
eec7dbd31e remove redundant max_running_reqs calculation in r3 (#16629) 2026-01-08 09:45:21 +08:00
Simo Lin
109fe03ad1 [smg][ci] Migrate Response API e2e tests to shared infrastructure (#16680)
Co-authored-by: Chang Su <chang.s.su@oracle.com>
Co-authored-by: key4ng <rukeyang@gmail.com>
2026-01-07 17:40:03 -08:00
Changyi Yang
bb798a1c26 [diffusion] fix: reduce default text length for Qwen-Image from 1024 to 512 (#16445) 2026-01-08 09:32:21 +08:00
Baizhou Zhang
38dc5839dd [1/n]deepseek_v2.py Refactor: attention backend handlers and forward method definition (#16306) 2026-01-08 09:22:31 +08:00
Hexq0210
5e867f60cf [NPU] Update model and features supported (#16652) 2026-01-08 09:13:30 +08:00
gongwei-130
65bed8382b Add google-cloud-storage into Dockerfile (#15343) 2026-01-07 16:54:45 -08:00
Harish
156d97b219 Fix KeyError when logprobs=false in completions endpoint (#16095) 2026-01-07 15:49:02 -08:00
b8zhong
24b30f7757 MoE Refactor: Refactor fp8.py -> flashinfer_trllm.py (#15151)
Co-authored-by: Brayden Zhong <b8zhong@users.noreply.github.com>
2026-01-07 15:35:00 -08:00
Alison Shao
3a4767daa3 Fix pytest tests to exit with proper exit code (#16681) 2026-01-07 15:20:46 -08:00
Simo Lin
6037267f5b [smg][ci] Add thread safety to ModelPool and GPUAllocator (#16674) 2026-01-07 13:25:41 -08:00
Alison Shao
0241e0460f Migrate tokenizer tests to test/registered/tokenizer/ (#16457) 2026-01-07 13:21:16 -08:00
Alison Shao
0c474273c5 Fix gpt_oss_common import path and migrate core tests (#16426) 2026-01-07 12:58:32 -08:00
Michael
3e73e12458 Revert "Add SwapAB Optimization for triton fused_moe_kernel on SM90." (#16676) 2026-01-07 11:24:47 -08:00
Douglas Yang
f4742558ac fix: 8-gpu-b200 increase timeout length (#16658) 2026-01-07 09:45:55 -08:00
Simo Lin
7385834c8d Add reference counting to ModelInstance for parallel test safety (#16672) 2026-01-07 08:28:15 -08:00
Ziwen Zhao
b5a94f8a8e [model-gateway] Fix IGW routing for external OpenAI workers (#16633) 2026-01-07 08:15:23 -08:00
Simo Lin
c356ed03dd refactor(e2e): unify RouterInstance into Gateway class, split conftest.py into modular fixtures (#16671) 2026-01-07 07:50:28 -08:00