Commit Graph

1320 Commits

Author SHA1 Message Date
Yuhao Yao
e9e7f15eb5 [bugfix] fix TBO crashes when attn_tp_size > 1 (#13730)
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
2025-12-11 18:18:40 -08:00
Alison Shao
e59435c34b Add retry logic for scheduled CI tests (#14771) 2025-12-11 16:59:58 -08:00
Zaili Wang
d6bd2d1126 [CPU] layernorm & fused add-layernorm kernels (#14074) 2025-12-11 16:58:23 -08:00
amysaq2023
70758d457e support non-disturbing remote-instance-weight-loader (#13125)
Signed-off-by: Anqi Shen <amy.saq@antgroup.com>
2025-12-11 16:45:32 -08:00
Liangsheng Yin
543d62d11a Introduce server_fixtures in sglang.test (#14899) 2025-12-11 22:30:33 +09:00
Vladimir221
27032cecd9 [Ascend]Support of piecewise graph compilation for prefill on NPU (#12287)
Co-authored-by: ronnie_zheng <zl19940307@163.com>
2025-12-11 21:10:07 +08:00
liupeng374
388018a5bd [NPU] adapt dsv3.2 nsa prefill context parallel (#14541) 2025-12-11 20:12:59 +08:00
Trang Do
8642dbe416 Refactor Marlin MoeRunner (#14554)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
2025-12-10 19:15:00 -08:00
Binyao Jiang
312df1d6c0 Fix TestGLM41VPPAccuracy test flakiness (#14848) 2025-12-10 16:59:58 -08:00
michael-amd
c97ce39181 [AMD] Add model to AMD nightly test (#14442) 2025-12-10 11:59:44 -08:00
Yuhao Yang
c1bd5ee8c5 Revert transformers to 4.57.1 (#14801) 2025-12-10 11:04:36 -08:00
Liangsheng Yin
503880dbbe [CI] fix UT success check in test_eagle_infer_beta_dp_attention.py (#14831) 2025-12-11 01:00:50 +09:00
Yuan Luo
03836d85d2 [GLM-4.6V] Support Pipeline Parallelism for GLM-4.6V & GLM-4.1V (#14720)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
2025-12-10 16:40:12 +08:00
b8zhong
56e5c07424 fix b200 fa4 ci (#14788) 2025-12-10 00:03:43 -08:00
b8zhong
b0a25d0913 fix b200 ci (#14786) 2025-12-09 23:08:41 -08:00
Ethan (Yusheng) Su
0c63fb9420 [Feature] Add LoRA support for embedding layers (#14177)
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: Beichen-Ma <bm685@cornell.edu>
2025-12-09 15:53:33 -08:00
b8zhong
55504df2f7 Add FP8 Blockwise GEMM Backend Flag --fp8-gemm-backend (#14379) 2025-12-09 12:05:56 -08:00
Alison Shao
13680e5542 [Test] Skip STANDALONE speculative decoding tests for different hidden sizes (#14733) 2025-12-09 22:21:35 +09:00
Xiaoyu Zhang
53d170883a Add fuse_marlin_moe test to ci and add new ep test (#14686) 2025-12-09 20:17:38 +08:00
Rain Jiang
f0e948a0f1 fix the deepep 8 gpu unit test (#14601) 2025-12-09 01:40:09 -08:00
Alison Shao
9a426fc5ef [CI] Move mistral large 3 basic to nightly (#14622) 2025-12-09 00:28:44 -08:00
b8zhong
0f8bd55f3e [CI] Fix Llama 3.1 8B FP4 CI (#14699) 2025-12-08 22:27:15 -08:00
Alison Shao
e6f0ddda44 [CI] Migrate Eagle 1-GPU tests to test/registered/ (#14529) 2025-12-09 12:56:36 +09:00
Baizhou Zhang
e5201bda34 [CI] Unblock gb200 cutedsl test (#14469) 2025-12-08 17:58:25 -08:00
Baizhou Zhang
6799847ebf [CI]Unblock and split spec v2+dp test (#14551) 2025-12-07 17:39:25 -08:00
Baizhou Zhang
673c11ba73 [Minor] Temporarily skipping deepep large mtp test (#14586) 2025-12-07 13:59:16 -08:00
b8zhong
3b47973af8 [CI] Tiny speed up VLM CI (#14517)
Co-authored-by: Brayden Zhong <b8zhong@users.noreply.github.com>
2025-12-07 13:30:41 -08:00
khalilzhk
948b6acee8 [BugFix] fix prefixcache performance and accuracy on ascend (#13573) 2025-12-08 02:16:20 +08:00
Liangsheng Yin
125e17efd5 Add small model test for spec v2 + dp + trtllm_mla (#14576) 2025-12-07 23:55:00 +08:00
Hanming Lu
e592ee6545 [Qwen3-next] remove heuristics and add radix cache kl test (#14520) 2025-12-06 12:11:40 -08:00
Baizhou Zhang
bc388471d2 [1/n] Fix hanging during DeepGemm Warmup (#14493) 2025-12-06 10:44:02 -08:00
Baizhou Zhang
42fcf5438f Revert "tiny remove deprecated endpoint call" (#14533) 2025-12-05 23:48:54 -08:00
blzheng
d257bf87b9 [CPU] add mamba fla kernels for Qwen3-next (#12324) 2025-12-06 14:16:23 +08:00
fzyzcjy
3d1b591aa1 Tiny use trtllm_mha as default when possible (#14291) 2025-12-05 14:26:03 -08:00
Alison Shao
16e8463a90 Add Mistral Large 3 basic test to PR CI (#14460) 2025-12-05 10:38:52 -08:00
b8zhong
ec7b2c16d9 tiny remove deprecated endpoint call (#13607) 2025-12-05 09:54:49 -08:00
roikoren755
889b46ea50 [Spec] Mamba2 support in target models (#13434) 2025-12-06 00:50:46 +08:00
Xinyuan Tong
6d37e70883 ministral3 (#14251)
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Yueming Yuan <yy28@illinois.edu>
2025-12-04 14:31:26 -08:00
jianan-gu
70d2587324 [CPU] Optimize small oc GEMM for Qwen3-next on CPU (#12446)
Co-authored-by: Zheng, Beilei <beilei.zheng@intel.com>
2025-12-04 00:38:47 -08:00
Even Zhou
894c0dc57c [NPU][1/N] NPU basic functions refactor and new modelslim quant type (#13359) 2025-12-04 16:15:31 +08:00
Ma Mingfei
f90b400431 [CPU] add support for mamba causal conv1d for qwen3-next (#12309) 2025-12-04 13:41:42 +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
blzheng
974c562a25 [CPU] add fused_qkvzba_split_reshape_cat kernel for Qwen3-next (#12330) 2025-12-03 23:46:08 +08:00
Liangsheng Yin
24903b88ba Tiny adjust CI testcases (#14362) 2025-12-03 21:19:51 +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
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
Yuan Luo
26aebf83d3 [VLM] Support Piecewise CUDA Graph for Qwen3-Omni-MOE (#14222)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
2025-12-02 10:12:10 +08:00