Commit Graph

6437 Commits

Author SHA1 Message Date
Xiaoyu Zhang
24616c5234 [Diffusion] Qwen image edit support qknorm optimization (#16062) 2025-12-29 21:37:24 +08:00
cklxx
d48723b77d Clamp logprob tokens with model vocab size (#14414) 2025-12-29 20:37:07 +08:00
Xiaoyu Zhang
f3d73b0199 [Diffusion] Refactor qwen_image's rope in a single helper func (#16047) 2025-12-29 17:24:26 +08:00
Xuchun Shang
4ab66d956f [HiCache] Fix deadlock when creating new group (#15805)
Signed-off-by: Xuchun Shang <xuchun.shang@gmail.com>
2025-12-29 17:13:04 +08:00
Xiaoyu Zhang
8305dc1718 [Diffusion] Disable packed QKV for FLUX & Z-Image (#16038) 2025-12-29 14:33:05 +08:00
Liangsheng Yin
a435f55d18 Tiny print launch command with shlex (#16010) 2025-12-29 11:26:46 +08:00
Mike Qiu
2ec6fa3c54 feat PD: add eagle3 support for DeepSeek V3 in EP mode (#14280)
Signed-off-by: Michael Qiu <qiudayu.qdy@antgroup.com>
Co-authored-by: Mike_Qiu <qiudayu.qdy@antgroup.com>
2025-12-29 11:12:34 +08:00
Li Jinliang
b840d6aaeb [diffusion] webui: reference to content task and better visualization capabilities (#16017) 2025-12-29 10:22:21 +08:00
EkiRui
ef4b3c0e96 Add host tensor allocator for memory_pool_host and support Mooncake standalone storage (#14873)
Signed-off-by: Xingrui Yi <yixingrui@linux.alibaba.com>
Co-authored-by: Teng Ma <sima.mt@alibaba-inc.com>
2025-12-28 16:28:50 -08:00
Cheng Wan
6f9d0a89a0 [scheduler] fix: correcting extend_logprob_start_len calculation (#15922) 2025-12-28 14:57:04 -08:00
Mick
d7a3336ebe [diffusion] fix: fix stages not logged when perf_dump_path is provided (#16016) 2025-12-28 23:17:43 +08:00
Xiaoyu Zhang
7d02c8e59f [JIT kernel] CI support jit kernel tests (#15939) 2025-12-28 23:11:02 +08:00
Lianmin Zheng
e6d5a213ad Fix metrics (#15998) 2025-12-28 05:03:49 -08:00
Mick
9f8e23071a [diffusion] chore: fix default offload setting for image generation model (#15928) 2025-12-28 20:45:33 +08:00
fzyzcjy
d90f9bfc4e Temporarily disable temp_prefill_info assertion to unblock CI (#16008) 2025-12-28 20:13:06 +08:00
Mick
3881bc8d0b [diffusion] CI: relax threshold by supporting different profiles (#16002) 2025-12-28 20:05:07 +08:00
Liangsheng Yin
be3828a13b Tiny cleanup duplicate code for multi-layer eagle worker. (#16004) 2025-12-28 18:08:20 +08:00
lif
5969be2f06 Apply fixture-kit mode to MMMUVLMMixin (#15615) 2025-12-28 17:22:05 +08:00
Liangsheng Yin
bf90ea9c5b Unify spec v2's naming manner. (#15990) 2025-12-28 14:14:52 +08:00
TZHelloWorld
0294844f04 [fix]deepgemm precompile when warmup (#15891) 2025-12-28 13:47:39 +08:00
Alison Shao
0e536600e8 Refactor: separate CI-specific weight validation into dedicated module (#15216)
Co-authored-by: Kangyan-Zhou <zky314343421@gmail.com>
2025-12-27 20:50:39 -08:00
Vladislav Nosivskoy
d70c265533 SGLang Tracing: fix attribute errors (header extraction & bootstrap span closing) (#15693)
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>
2025-12-27 22:44:31 -06:00
Baizhou Zhang
656f4d69a1 Refactor fp8 nextn layer for DeepSeek nvfp4 checkpoint (#15353) 2025-12-28 11:57:09 +08:00
DarkSharpness
8e43980ebb [Feature] JIT Fused QK norm + qk norm clean up (#15835) 2025-12-28 11:53:50 +08:00
Mick
b4a00ed2d9 [diffusion] chore: clean ComposedPipelineBase (#15937) 2025-12-28 11:43:25 +08:00
fzyzcjy
f55d608c89 Tiny fix cannot launch nvfp4 checkpoint with bf16 kv cache (#15986) 2025-12-28 11:22:20 +08:00
Ho-Ren (Jack) Chuang
349ce2dd19 Support kv8 (FP8) with torch_native attention backend (#12596)
Signed-off-by: Ho-Ren (Jack) Chuang <horenchuang@bytedance.com>
2025-12-28 10:48:30 +08:00
Lianmin Zheng
183b65190a Clean up logging (#15919) 2025-12-27 15:27:12 -08:00
Yuhao Yang
0cd2b719a5 [diffusion] chore: remove useless params (#15925) 2025-12-28 01:01:08 +08:00
Mick
39d56196a0 [diffusion] logging: log available gpu mem while loading and generating (#15936) 2025-12-28 00:34:58 +08:00
Hudson Xing
5c393e8153 Fix temp_prefill_info assertion error in PP disaggregation mode (#15943) 2025-12-27 22:46:55 +08:00
Ratish P
ca740a41f3 [model-gateway]: fix grpc embedding test (#15934) 2025-12-27 05:56:54 -05:00
jiaming1130
60a230b1fd [NPU] Support w4a8 with activation clip (#14736)
Co-authored-by: ZhengdQin <46387172+ZhengdQin@users.noreply.github.com>
2025-12-27 16:19:46 +08:00
Mick
aa89c6a7e2 [diffusion] refactor: unify model loading and offloading behavior (#15923) 2025-12-27 16:18:24 +08:00
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