Commit Graph

5403 Commits

Author SHA1 Message Date
Ke Bao
faecd37ed4 Add Mimo-v2-flash model to ci test (#15887) 2025-12-27 14:18:08 +08:00
Liangsheng Yin
9ad546d7e8 Tiny cleanup the models' name in test_utils (#15920) 2025-12-27 14:13:23 +08:00
Yuhao Yang
29ce7b3612 [diffusion] chore: remove stepvideo code (#15918) 2025-12-27 13:25:05 +08:00
Lianmin Zheng
a8380ded71 Add a test case for crash dump (#15905) 2025-12-26 19:39:28 -08:00
Zheng Wengang
cd3289c7a4 [BugFix][VLM] Correct weight loading with tie_word_embeddings == False (#15398) 2025-12-26 17:30:50 -08:00
Cheng Wan
2ec57cefd9 hotfix: add type hints to scheduler mixins (#15916) 2025-12-26 17:08:11 -08:00
Cheng Wan
988b14ca0e refactor: add type hints to scheduler mixins (#15913) 2025-12-26 16:50:07 -08:00
Lianmin Zheng
93495dcac9 Revert "[VLM] Refactor load_mm_data to improve performance" (#15911) 2025-12-26 13:43:18 -08:00
Ratish P
886e038329 [model-gateway]: fix crash in embedding worker health check (#15910) 2025-12-26 12:57:13 -08:00
Muqi Li
01bd0d3e8b [Tool Call][DSV32] Streamline function call parameters (#14750)
Signed-off-by: Muqi Li <muqi1029@gmail.com>
2025-12-26 11:35:30 -08:00
Lianmin Zheng
43e1bbc0d5 Revert "[feat] Init support for webui-I2I" (#15906) 2025-12-26 09:53:03 -08:00
Li Jinliang
59b12996fb [diffusion] apps: support I2I tasks in webui (#15778) 2025-12-26 23:45:11 +08:00
Mick
b70914969b [diffusion] CI: support returning request id from endpoint (#15844)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-12-26 23:38:03 +08:00
Xiaoyu Zhang
51dbdb2202 [diffusion] improve: improve qwen-image-edit performance to align with LightX2V (#15812)
Co-authored-by: Mick <mickjagger19@icloud.com>
2025-12-26 22:25:10 +08:00
Mick
8dc6f0fc4d [diffusion] refactor: centralize hardware platform detection and streamline environment variable management (#15842) 2025-12-26 22:16:18 +08:00
Huaixin Chang
cf34d0ab32 [Fix] assert error in log_prefill_stats (#15881)
Signed-off-by: Chang Huaixin (OpenAnolis) <changhuaixin@linux.alibaba.com>
Co-authored-by: Junjie Mao (Alibaba) <banxing.mjj@alibaba-inc.com>
2025-12-26 19:54:35 +08:00
Prozac614
3778c2fc6d [diffusion] CI: fix CI test case skip problem (#15874)
Co-authored-by: Mick <mickjagger19@icloud.com>
2025-12-26 19:42:20 +08:00
fzyzcjy
5d421db883 Tiny log warn users when tracing is automatically disabled (#15889) 2025-12-26 19:00:37 +08:00
shuwenn
fe3d47fc9d fix: warn once per env var key (#15846) 2025-12-26 18:41:15 +08:00
Yi Zhang
ef92b4eb88 [BUGFIX] fix edge case for qwen3-next (#14209) 2025-12-26 17:14:37 +08:00
Annis
73c0c66ff8 [diffusion] ZImage support Tensor Parallel (#15849) 2025-12-26 14:58:14 +08:00
chhnb
a1e9b4edfa diffusion: support Qwen-Image-Layered (#15817)
Co-authored-by: yhyang201 <yhyang201@gmail.com>
2025-12-26 14:57:01 +08:00
Liangsheng Yin
e75657c839 [Bug] fix piggyback load report return None bug (#15870) 2025-12-26 14:48:45 +08:00
Ke Bao
c28c536c91 Fix swa available memory check (#15867) 2025-12-26 13:19:01 +08:00
Yuan Luo
086813ae8a [VLM] refactor: refactor load_mm_data to improve performance (#14644)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
2025-12-26 13:17:53 +08:00
Hexq0210
3fd232ad96 [NPU] update Mixed chunk op to FIA (#15518) 2025-12-26 12:17:40 +08:00
Liangsheng Yin
cb1812954a Introduce ModelRunnerKVCacheMixin to simplify the code. (#15821) 2025-12-26 11:17:33 +08:00
Kangyan-Zhou
a91e072f33 Use allow auto truncate in the OpenAI API endpoint (#15369) 2025-12-25 18:45:57 -08:00
fzyzcjy
0271fc3456 Fix prefill num tokens metrics (#15858) 2025-12-26 10:26:42 +08:00
fzyzcjy
68bece8caa Super tiny move last_prefill_tokens to metrics mixin (#15857) 2025-12-26 10:26:10 +08:00
Ke Bao
7b7e357f61 Separate swa and local attention chunk cache eviction (#15820) 2025-12-26 09:34:22 +08:00
Ke Bao
2f66b0671b Fix chunk_kda_fwd missing argument (#15851) 2025-12-26 09:32:35 +08:00
Alison Shao
4805118122 ci: add continue-on-error for scheduled PR tests (#15701) 2025-12-25 13:26:14 -08:00
Hudson Xing
9d878c1f3e Optimize FP8 MLA KV cache writes with Triton kernel (#15522) 2025-12-25 12:35:39 -08:00
Lianmin Zheng
8087ef126f Clean up the __init__ of TokenizerManager and DetokenizerManager (#15796) 2025-12-25 10:30:27 -08:00
Mick
a355911909 [diffusion] improve: improve post-processing by moving compute-intensive tasks to GPU (#15822) 2025-12-26 01:29:04 +08:00
Yuxuan Zhang
f3ba711662 fix: change class name of GLM-ASR (#15772) 2025-12-26 00:15:16 +08:00
Yuwei An
5c243ba588 Custom All Reduce for Piecewise Cuda Graph (#15356)
Signed-off-by: Oasis-Git <ayw.sirius19@gmail.com>
2025-12-25 23:55:15 +08:00
StonyPort
b6702d72cf feat: log request when e2e latency exceeds the specified value (#15759)
Co-authored-by: qiuxuan.lzw <qiuxuan.lzw@alibaba-inc.com>
Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>
2025-12-25 23:12:35 +08:00
fzyzcjy
c12567274a Tiny change bench-serving to use routing key header (#15827) 2025-12-25 21:29:49 +08:00
Yingchun Lai
bb9e6cdf9e [MiMoV2Flash] fix: respect --swa-full-tokens-ratio arg (#15488) 2025-12-25 21:02:56 +08:00
roikoren755
de03b0cd30 [Nemotron 3 Nano] Add triton MoE configs (#15815)
Signed-off-by: Roi Koren <roik@nvidia.com>
2025-12-25 19:31:20 +08:00
Mick
2a8a785634 [diffusion] log: avoid logging in hot path if unnecessary (#15818) 2025-12-25 18:42:52 +08:00
Liangsheng Yin
f4e835af2f Cleanup ModelRunner (#15802) 2025-12-25 18:13:30 +08:00
Xiaoyu Zhang
e6ce16a4c2 [diffusion] feat: support TP for Flux.1.dev (#15666)
Co-authored-by: Mick <mickjagger19@icloud.com>
2025-12-25 18:00:44 +08:00
Xiaoyu Zhang
de2f2880b5 [JIT sgl-kernel] Jit support per tensor quant (#15709) 2025-12-25 16:24:37 +08:00
zhangheng
a89e85e739 [1/N][Sparse With Hicache]: Add Sparse Interface (#14741)
Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com>
Co-authored-by: huangtingwei <141888744+huangtingwei9988@users.noreply.github.com>
Co-authored-by: MagicYang1573 <1328657938@qq.com>
2025-12-25 00:12:47 -08:00
Ke Bao
cbf9f13493 Adjust server args for Mimo-v2-flash model (#15803)
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
2025-12-25 16:04:39 +08:00
Yi Zhang
eb3da9c1dd fuse ssm state store into chunk_gated_delta_rule_fwd_h (#15409) 2025-12-25 16:03:15 +08:00
Yuan Luo
b9af8d2eb9 [VLM] Support apply qk norm in multi cuda streams (#15720)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
2025-12-25 14:35:07 +08:00