Commit Graph
3393 Commits
Author SHA1 Message Date
Sy03 118f646c87 [CI] Retrigger CosyVoice3 ready validation
Signed-off-by: Sy03 <1370724210@qq.com>
2026-10-02 22:56:24 +08:00
Sy03 7d5a6bc5cb [Doc] Clarify CosyVoice3 lazy graph latency and memory headroom
Signed-off-by: Sy03 <1370724210@qq.com>
2026-10-02 22:56:24 +08:00
Sy03 8361765b33 [Model] Minimize CosyVoice3 streaming regression tests
Signed-off-by: Sy03 <1370724210@qq.com>
2026-10-02 22:56:24 +08:00
Sy03 b3c25a608d [Model] Optimize CosyVoice3 packed streaming with bounded HiFT graphs
Signed-off-by: Sy03 <1370724210@qq.com>
2026-10-02 22:56:24 +08:00
Nick CaoandCodex 0e6791e9c4 [Bugfix] Initialize eager state in Higgs test fixture (#8426)
Signed-off-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Codex <noreply@openai.com>
2026-10-02 10:22:52 -04:00
Zheng Wengangandamy-why-3459 eb1699bfca [FEAT][Fronted] Support incremental prefill for realtime video streaming (#5894)
Signed-off-by: ZhengWG <zwg0606@gmail.com>
Signed-off-by: Zheng Wengang <zwg0606@gmail.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
2026-10-02 22:18:51 +08:00
Sy03 e372aa3a41 [Bugfix] Restore Fish Speech and CosyVoice3 audio quality at high concurrency (#8422)
Signed-off-by: Sy03 <1370724210@qq.com>
2026-10-02 07:11:04 -07:00
ae58c2d8b9 [Model] YuE2: async single-stage synthesis and CUDA graph acceleration (#8407)
Signed-off-by: Sy03 <1370724210@qq.com>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: Wang Zhipeng <wangzhipeng628@gmail.com>
Co-authored-by: princepride <wangzhipeng628@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-02 05:17:06 -07:00
b10270a01c [AR-Diffusion] Page in kernel-legal blocks so the default resolution can run (#6481)
Signed-off-by: linzhenpl07 <linzhenpl07@gmail.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: Zhou Taichang <tzhouam@connect.ust.hk>
2026-10-02 20:05:04 +08:00
Sy03 e84014dffb [Model] Add single-stage Qwen3-TTS with in-Talker streaming codec decode (#8259)
Signed-off-by: Sy03 <1370724210@qq.com>
2026-10-02 21:34:30 +10:00
Rahul Steiger 596487fe62 [Core] Prototype diffusion attention execution contracts with FA4 (#7379) 2026-10-02 17:58:47 +08:00
MaciejBalaNVand汪志鹏 97d6c693a6 [feature] Add HSDP pre-sharded option (#7948)
Signed-off-by: Maciej Bala <mbala@nvidia.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
2026-10-02 09:35:09 +00:00
汪志鹏 b742f86136 [CI/Build] Restore streaming executor fixture contract (#8418)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-10-02 01:45:56 -07:00
andyluo7 53c7340668 test: measure offload memory inside diffusion workers (#8189)
Signed-off-by: andyluo7 <andy.luo@amd.com>
2026-10-02 14:07:20 +08:00
Sy03 d93e1a8e09 [Model] Optimize Qwen3-Omni MRv2 handoff, code prediction and audio decoding (#8223)
Signed-off-by: Sy03 <1370724210@qq.com>
2026-10-01 22:22:54 -07:00
wtz2333andYuanheng Zhao 68003cf6ad [Bugfix] Fix washed-out LingBot Video outputs (#7037)
Signed-off-by: wtz2333 <2955110911@qq.com>
Co-authored-by: Yuanheng Zhao <54058983+yuanheng-zhao@users.noreply.github.com>
2026-10-02 03:57:50 +00:00
andyluo7 bbee488da3 fix: repair ROCm test routing, CPU timeouts, and Breeze autotuning (#8342)
Signed-off-by: andyluo7 <andy.luo@amd.com>
2026-10-02 07:36:41 +08:00
Joshna-MedisettyandCursor 2560f91859 fix(ming): build ISTFT spectrogram in float32 (#7538)
Signed-off-by: Joshna Medisetty <joshna.medisetty@intel.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 22:45:09 +00:00
Doug Smith 7b15d22f48 [CI/Build] Package runtime data explicitly (#7956)
Signed-off-by: Doug Smith <dosmith@redhat.com>
2026-10-01 19:10:21 +00:00
Youyuan Liandprincepride 423f34326e [Model] Add YuE2-3B text-to-music (model + /v1/audio/speech adapter) (#7886)
Signed-off-by: Youyuan Li <105433145+Darcy-Lee@users.noreply.github.com>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Co-authored-by: princepride <wangzhipeng628@gmail.com>
2026-10-01 18:04:31 +08:00
汪志鹏 a038b38179 [Model] Add MiniMax-H3 latent super-resolution and hi-res refinement (#8322)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2026-10-01 14:24:40 +08:00
yzhautouskay 27a6321a63 [Model][Cosmos3] Keep diffusion sampling state in FP32 (#7592)
Signed-off-by: Yuliya Zhautouskaya <yzhautouskay@nvidia.com>
2026-09-30 11:35:51 -07:00
amy-why-3459 4af28f33bd [Bugfix] Defer VoxCPM2 NPU patch to avoid platform import cycle (#8330)
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
2026-09-30 05:25:36 -07:00
Sy03 56763cd6c3 [Model] Enable Higgs Audio v3 MRV2 streaming and fix mixed-prefill capture bounds (#8226)
Signed-off-by: Sy03 <1370724210@qq.com>
2026-09-30 11:32:27 +00:00
psv666andamy-why-3459 b44b2f981c [Bugfix] Fix Qwen3-Omni audio-input mean_e2el_ms regression (#8306)
Signed-off-by: psv666 <2693925048@qq.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
2026-09-30 18:07:55 +08:00
Alicia c524e1a879 [CI/Build] Refresh targeted perf baselines (#6538)
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
2026-09-30 09:24:25 +00:00
wangyuandAlicia d0f073686a [CI/Build] Split long weekly TTS jobs and route slow full-model cases to nightly (#8239)
Signed-off-by: wangyu <410167048@qq.com>
Co-authored-by: Alicia <115451386+congw729@users.noreply.github.com>
2026-09-30 09:08:24 +00:00
004a5711dc [Bugfix][Helios] Guard cross-attn KV cache against address reuse (#8064)
Signed-off-by: yancaocn <yancaochn@163.com>
Co-authored-by: yancaocn <yancaochn@163.com>
Co-authored-by: Zhou Taichang <tzhouam@connect.ust.hk>
2026-09-30 16:44:51 +08:00
WeiQing Chen e34f8c4f42 [Doc] Update vLLM-Omni WeChat QR code (#8301)
Signed-off-by: David Chen <530634352@qq.com>
2026-09-30 11:39:05 +08:00
aa41a3ac97 [Bugfix] Fix the remaining Python 3.10 breakages (#7985)
Signed-off-by: Armaan Amatya <armaanamatya2014@gmail.com>
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-09-30 11:38:23 +08:00
Hongchen Liandredearly123 989161c49d [Benchmark] Add MammothModa2 startup/loading breakdown (#7312)
Signed-off-by: redearly123 <65453204+redearly123@users.noreply.github.com>
Co-authored-by: redearly123 <65453204+redearly123@users.noreply.github.com>
2026-09-30 11:38:07 +08:00
Mu GuanLinandHongsheng Liu 3a82c85880 [Experimental][Perf] Eliminate redundant host copies from generated-video transport (#7355)
Signed-off-by: mglyn <1203789601@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-09-30 11:37:57 +08:00
Egor Chernobrovkin c27a52a359 [Model] Make VoxCPM2 generation settings configurable (#7010)
Signed-off-by: Egor Chernobrovkin <33jasooon33@gmail.com>
2026-09-30 11:26:12 +08:00
vOv 25bdb38b11 [Bugfix] Do not block diffusion client shutdown on a dead subprocess (#7812)
Signed-off-by: cr-gao <gaochenrui@sjtu.edu.cn>
2026-09-30 11:25:37 +08:00
Yueqian Lin 146ccc133a [Perf][AuK] Compile the DiT step, use cuDNN attention and warm up at startup (#8300)
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
2026-09-30 11:21:21 +08:00
yulunandHongsheng Liu 9097fa6547 [Hardware][Ascend] Accelerate VoxCPM2 LocDiT with NPUGraph (#7275)
Signed-off-by: Big2Wheel <1404207590@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-09-30 10:11:22 +08:00
35cf6ac355 [Feat][Perf][AuK]Support Online Serving and DiT CUDAGraph (#7469)
Signed-off-by: boatman <109857087+sphinxkkkbc@users.noreply.github.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
2026-09-30 00:18:38 +00:00
BruceLoveDecimalandYueqian Lin 3a28882946 [Perf][Auk] VAE cuda graph and tiling (#7881)
Signed-off-by: liuqihao <liuqihao970610@gmail.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
2026-09-29 23:27:01 +00:00
vraitiandClaude Opus 4.6 8ad6e801f5 [Tests] Fix Qwen3-Omni E2E LiveKit Test (#8294)
Signed-off-by: vraiti <vraiti@redhat.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-09-29 16:23:28 -04:00
Sy03 5af3a16526 [Model] Add MiniCPM-o 4.5 turn-mode MRv2 and batched audio inference (#8222)
Signed-off-by: Sy03 <1370724210@qq.com>
2026-09-29 11:41:39 -07:00
jingchengtianandjingchengtian 43ef1e61fb [Perf][TTS] Add per-row generator support to MOSS-TTS talker to eliminate serial fallback for seeded batched requests (#7922)
Signed-off-by: jingchengtian <jingchengtian@users.noreply.github.com>
Signed-off-by: jingchengtian <tjc1995@126.com>
Co-authored-by: jingchengtian <jingchengtian@users.noreply.github.com>
2026-09-29 13:13:50 -04:00
Alex Brooks 764a109f66 [Config] Disable Async Chunk for Unsupported Pipelines (#5099)
Signed-off-by: Alex Brooks <albrooks@redhat.com>
2026-09-29 09:52:09 -06:00
Sy03andzack 1ea0ee3b38 [Model] Add opt-in packed Flow and batched HiFT inference for CosyVoice3 (#8224)
Signed-off-by: Sy03 <1370724210@qq.com>
Signed-off-by: zack <huixindaddy@yahoo.com>
Co-authored-by: zack <huixindaddy@yahoo.com>
2026-09-29 15:48:36 +00:00
Nick CaoandCodex c85f1a44fb [Bugfix] Break duplex OpenAI import cycle (#8287)
Signed-off-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Codex <noreply@openai.com>
2026-09-29 11:07:03 -04:00
andyluo7 f145f66c82 test: define Wan fused BF16 parity budget (#8188)
Signed-off-by: andyluo7 <andy.luo@amd.com>
2026-09-29 22:43:14 +08:00
Sy03 001f8a80b9 [Core] Extend the shared multi-stage execution framework for mixed V1/MRv2 pipelines (#8184)
Signed-off-by: Sy03 <1370724210@qq.com>
2026-09-29 07:40:57 -07:00
guangli_Liuandliuguangli 6b4173f50b [Bugfix] Fix Qwen3-Omni realtime routing with typed stage configs (#8279)
Signed-off-by: liuguangli <liuguangli35@gmail.com>
Co-authored-by: liuguangli <liuguangli35@gmail.com>
2026-09-29 10:23:11 -04:00
7d6904aa94 SeedVR2: bounded long-video restoration (#8102)
Signed-off-by: 0z5a <Dezhen.lu@student.uni-tuebingen.de>
Signed-off-by: 0z5a <dezhen.lu@uni-tuebingen.de>
Signed-off-by: 0z5a <dezhen.lu@student.uni-tuebingen.de>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Co-authored-by: 0z5a <dezhen.lu@uni-tuebingen.de>
Co-authored-by: princepride <wangzhipeng628@gmail.com>
2026-09-29 11:33:50 +00:00
Canlin Guo 235c430326 [Frontend] Tune reference cache limits and registered MOSS voice requests (#7883)
Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>
2026-09-29 04:10:17 +00:00
Ding Zuhao 1c1fdf719c [Bugfix][BAGEL] Keep replicated prefill and cache-update phases off the SP strategy (#8177)
Signed-off-by: Ding Zuhao <e1583181@u.nus.edu>
2026-09-29 03:45:49 +00:00