Commit Graph

11116 Commits

Author SHA1 Message Date
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
Simo Lin
de2799f3f5 [docs] Fix non-clickable ToC links in model gateway documentation (#16054) 2025-12-28 23:35:37 -08:00
Hexq0210
f784cbfa92 Update model and feature support for Ascend NPU (#16003) 2025-12-29 15:16:25 +08:00
Simo Lin
097330909f [model-gateway] update WorkerRegistryStats with connection mode and circuit breaker info (#16046) 2025-12-28 23:14:57 -08:00
Simo Lin
a44d0079f8 [ci] update genai bench to 0.0.3 for pd testing (#16051) 2025-12-28 23:14:44 -08:00
Xiaoyu Zhang
8305dc1718 [Diffusion] Disable packed QKV for FLUX & Z-Image (#16038) 2025-12-29 14:33:05 +08:00
Simo Lin
ec8c831d5a [model-gateway]: optimize metrics for minimal CPU and memory overhead (#16041) 2025-12-28 22:28:08 -08:00
Simo Lin
f13949e5a9 [model-gateway] perf: optimize observability logging for minimal CPU/memory overhead (#16039) 2025-12-28 21:20:46 -08:00
Simo Lin
c236a3fdf0 [model-gateway][CI] Display benchmark results in GitHub Actions summary (#16037) 2025-12-28 20:57:27 -08:00
Simo Lin
41a1d16b02 [model-gateway] Organize CLI arguments into logical groups for better --help output (#16035)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-12-28 20:25:53 -08:00
Simo Lin
9884c9fd4c [model-gateway] Organize Rust CLI arguments into logical groups for better --help output (#16036) 2025-12-28 20:25:38 -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
Lianmin Zheng
c58a573a40 [Docs] Improve documentation index page (#16028) 2025-12-28 18:44:52 -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
Baizhou Zhang
208e6a9dac [Doc]Update MTP moe backends for EP document (#16013) 2025-12-28 19:36:23 +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
fzyzcjy
8fab48952e Tiny fix WASM test errors on machines with many cores (#15992) 2025-12-28 17:12:04 +08:00
fzyzcjy
7ccaec6467 Add micro benchmarks for manual policy (#15991) 2025-12-28 17:11:56 +08:00
Cheng Wan
c457aad54a Update test parameters for deepep_large test (#16001) 2025-12-28 00:58:19 -08:00
Liangsheng Yin
c7e7bfa32c Add EAGLE3 test with MMLU dataset. (#15945) 2025-12-28 16:07:58 +08:00
Liangsheng Yin
bf90ea9c5b Unify spec v2's naming manner. (#15990) 2025-12-28 14:14:52 +08:00
fzyzcjy
26c5091217 Tiny extract PeriodicTask in router (#15988) 2025-12-28 14:07:13 +08:00
fzyzcjy
325a4c1945 Tiny add smg_manual_policy_cache_entries metric (#15987) 2025-12-28 14:07:07 +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
Hudson Xing
474a4699c5 Add correctness validation for decode_attention test (#15806) 2025-12-28 11:46:17 +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
Ratish P
2af955e16c [model-gateway]: remove unnecessary comment (#15947) 2025-12-27 13:33:02 -05:00
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
Shangming Cai
41addd2e08 chore: bump mooncake version to 0.3.8 (#15886)
Signed-off-by: Shangming Cai <csmthu@gmail.com>
2025-12-27 23:34:24 +08:00
Hudson Xing
5c393e8153 Fix temp_prefill_info assertion error in PP disaggregation mode (#15943) 2025-12-27 22:46:55 +08:00
Simo Lin
3645ed0f73 [model-gateway] Add PrefixHash load balancing policy for KV cache-aware routing (#15935) 2025-12-27 05:58:05 -05:00