Commit Graph

6650 Commits

Author SHA1 Message Date
ishandhanani
885cfca273 ci: try to fix gpg error during kernel build (#12928) 2025-11-09 11:45:29 -08:00
Liangsheng Yin
4e916f9840 [lint] tiny fix unimported packages. (#12927) 2025-11-10 00:59:10 +08:00
Liangsheng Yin
4f65a64666 Refactor / Unify event loop across PD-Disagg, Overlap, DP-Attn cases (#12839)
Co-authored-by: cctry <17473714+cctry@users.noreply.github.com>
2025-11-10 00:42:50 +08:00
Mick
f5b3ccd9a5 feat: basic support for server-level multimodal cache (#10775) 2025-11-10 00:27:50 +08:00
Ke Bao
bb00e24f87 Adjust server launch time in ci (#12917) 2025-11-09 20:41:29 +08:00
Liangsheng Yin
210a9cab6d [CI] Fix matrix.part in pr-test. (#12920) 2025-11-09 18:53:18 +08:00
Teng Ma
b8ac4fcb51 [PD] feat: refactor custom mem pool and add barex pd support (#12332) 2025-11-09 18:51:34 +08:00
Liangsheng Yin
877cb52840 [CI] increase ut buckets & adjust estimation time. (#12919) 2025-11-09 18:17:50 +08:00
Zijian Zhang
3633f8b0cf Add Jet-Nemotron (#12448) 2025-11-09 01:32:47 -08:00
Kangyan-Zhou
93cf60fc64 Fix Deepseek nightly tests (#12906) 2025-11-09 00:26:06 -08:00
Ke Bao
b5e0417392 Add kimi k2 thinking to ci (#12907) 2025-11-09 16:10:32 +08:00
Minglei Zhu
8a821af793 fallback to triton mm_persistent kernel when deepGemm fail (#12911) 2025-11-08 23:42:26 -08:00
Kangyan-Zhou
4b1d163bfd Add HF cleanup logic in ci_install_dependency.sh (#12895) 2025-11-08 22:56:25 -08:00
Kangyan-Zhou
c21a3ec299 Fix duplicate nightly test name (#12905) 2025-11-08 21:38:48 -08:00
Ke Bao
b142831a26 Fix empty server args in marlin moe test (#12904) 2025-11-09 13:30:47 +08:00
Kangyan-Zhou
d134096319 Add Deepseek models into nightly tests (#12865) 2025-11-09 13:17:49 +08:00
Qiaolin Yu
f290e8016e Revert "Fix spec decoding acc length for dpsk-r1-fp4 tp8" (#12900) 2025-11-08 20:42:42 -08:00
Qiaolin Yu
9299a62fcb Fix spec decoding acc length for dpsk-r1-fp4 tp8 (#12896) 2025-11-08 19:55:45 -08:00
Liangsheng Yin
49543be9da Tiny simplify can_run_dp_cuda_graph gather logic (#12891) 2025-11-09 11:15:36 +08:00
Ke Bao
5236290399 Update CODEOWNERS (#12897) 2025-11-09 09:37:11 +08:00
sglang-bot
b2b26d4324 chore: bump sgl-kernel version to 0.3.16.post6 (#12889) 2025-11-09 09:16:28 +08:00
alisonshao
d3a03aeef8 Refs/heads/add nightly test multi gpu configs (#12870) 2025-11-08 15:14:50 -08:00
Baizhou Zhang
5f02b918ec [Fix] Fix trtllm-mla backend when chunked prefix cache is disabled (#12361) 2025-11-08 15:10:25 -08:00
b8zhong
49653c8896 use fast stream instead of torch.cuda.current_stream in llama 4 shared experts overlap (#12811) 2025-11-08 15:04:37 -08:00
Ke Bao
44f594d832 Apply moe_reduce_sum kernel for fused_marlin_moe (#12888) 2025-11-09 01:31:05 +08:00
fzyzcjy
2b6c4257a0 Fix sending all requests to the first rank in DP attention (#12832) 2025-11-09 00:18:53 +08:00
Liangsheng Yin
243ea585fc [DP-Attn] Clarify MLP sync / idle batch preparation logic (#12843) 2025-11-08 23:23:14 +08:00
Liangsheng Yin
6fee2c535c [CI] Tiny adjust CI esitmation time (#12886) 2025-11-08 23:02:19 +08:00
Charles Chen
f1a9c72de3 Support capturing aux_hidden_states for minimax m2. (#12798) 2025-11-08 01:54:22 -08:00
YAMY
190002c613 [Docs][DeepseekV3.2] Update deepseekv3.2 docs for mha short seq prefill (#12868) 2025-11-08 00:11:02 -08:00
Lianmin Zheng
0296f1cdad [Auto Sync] Update activation.py, logits_processor.py, rota... (20251107) (#12853)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Stefan He <hebiaobuaa@gmail.com>
2025-11-07 22:07:51 -08:00
Baizhou Zhang
e039ff382c [CI] Fix huggingface access for test_flash_attention_4.py (#12846) 2025-11-07 20:07:06 -08:00
hlu1
b8ddc296f4 [sgl-kernel][Deepseek V3.2] Add row_starts to topk kernel (#12582)
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
2025-11-07 18:33:27 -08:00
alisonshao
0b88d520a0 Add nightly performance test for GPT-OSS 4GPU models (#12805) 2025-11-07 16:54:07 -08:00
Keyang Ru
d3d7f960b5 [router] Switch MCP tests from DeepWiki to self-hosted Brave search server (#12849) 2025-11-07 16:16:07 -08:00
Chang Su
e434187289 [router][grpc] Move all error logs to their call sites (#12859) 2025-11-07 15:55:34 -08:00
Chang Su
fe19a580fb [router][grpc] Refactor: Add builders for chat and responses (#12852) 2025-11-07 15:43:32 -08:00
b8zhong
55e8e3999c add back flashinfer jit cache to dev docker (#12851)
Co-authored-by: Brayden Zhong <b8zhong@users.noreply.github.com>
2025-11-07 14:51:24 -08:00
Mingyi
32f7982800 sglang diffusion announcement (#12856) 2025-11-07 14:35:25 -08:00
Rain Jiang
0f76976c3c remove the fa4 page_size hardcode to 128 restriction on mla model arch (#12801) 2025-11-07 13:30:30 -08:00
Lianmin Zheng
ae62279071 Fix data parallel controller launch for num nodes > 2 (#12822) 2025-11-07 12:13:21 -08:00
Keyang Ru
5c9273c032 [router] Support structured model output for openai and grpc router (#12431) 2025-11-07 10:16:45 -08:00
Mick
e316bcacb1 update multimodal_gen readme (#12825)
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
2025-11-07 09:04:44 -08:00
Ke Bao
0fe9c1f70b Fix piecewise cuda graph ci test (#12836) 2025-11-08 00:25:00 +08:00
Yang Kaiyong
61bfd9fa9b optm(checkpoint-engine): disable multi-thread loading when update weights (#12374)
Signed-off-by: Yang Kaiyong <yangkaiyong.yky@antgroup.com>
2025-11-07 21:30:04 +08:00
Chen1022
c67fce160e Fix missing dp_max_padding argument in set_dp_buffer_len (#12812) 2025-11-07 21:27:43 +08:00
hlu1
bef37d6de8 [Deepseek V3.2] Only skip Indexer logits computation when is_extend_without_speculative (#12816)
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
2025-11-07 01:34:04 -08:00
Jonah Bernard
bc25ea6762 [MoE] Add Comprehensive MoE Integration Tests (#12090) 2025-11-07 00:34:46 -08:00
elvischenv
1fa788ec14 [Bugfix] Fix illegal memory access (#12758) 2025-11-06 21:59:57 -08:00
Johnsonms
125f76ea44 [Test] Add DeepSeekV3.2 NSA Indexer Test Suite (#12520) 2025-11-06 21:28:43 -08:00