anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
3,253 Commits 235 Branches 31 Tags
67aa30c96697e1aab4a135d5e673d2a457dffe9f
Commit Graph
3253 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Honghan ZhuandGao Han 67aa30c966 [Bugfix] Align MiniMax-H3 inference steps with denoiser evaluations (#7219) 
Signed-off-by: zhuhh97 <zhuhonghan@huawei.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
 2026-09-24 03:56:38 +00:00
wuli666 6daf5b30f0 [Bugfix] Preserve cancellation in duplex session control queues (#7782) 
Signed-off-by: wuli666 <421774554@qq.com>
 2026-09-23 19:32:40 +00:00
Joshna-Medisetty 5e6b9047c9 [Bugfix] Drain the omni connector output on the main thread in the AR runner (#7750) 
Signed-off-by: Joshna Medisetty <joshna.medisetty@intel.com>
 2026-09-23 11:36:56 -07:00
akshatvishu b4737d3066 [BugFix] Download Anima assets for README CI test (#7928) 
Signed-off-by: akshatvishu <akshatnayak197@gmail.com>
 2026-09-23 17:04:51 +00:00
Zhou Taichang d38566ae80 [Bugfix][Core] Fix stage initialization spawn-lock/device-lock inversion (#7926) 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-09-23 17:03:06 +00:00
summerandmultica-agent 7f867fb782 [Bugfix][Diffusion] Drop aborted request's orphaned async output (fix #6413) (#6439) 
Signed-off-by: summer <128961079+zhang-keliang@users.noreply.github.com>
Co-authored-by: multica-agent <github@multica.ai>
 2026-09-23 16:58:46 +00:00
NumberWan 1934d121e2 [Bugfix] Gate Qwen-Image fused QK-norm+RoPE on short sequences (#7780) (#7965) 
Signed-off-by: NumberWan <wantszkin2003@gmail.com>
 2026-09-23 16:12:29 +00:00
YancyAstheniaGao Han
 		a473ae78c3 [Bugfix][HunyuanImage3] Fix DiT LoRA binding: namespace alias + GQA QKV de-interleave (#6802) 
Signed-off-by: Asthenia <asthenia0412@gmail.com>
Signed-off-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: Asthenia <asthenia0412@gmail.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
 2026-09-23 16:06:54 +00:00
chickeytonandClaude Fable 5.1 21f167eacd [CI/Build][MiniCPM-o] Gate Seed-TTS WER over chat completions instead of the native duplex path (#7963) 
Signed-off-by: chickeyton <ngton2014@gmail.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-23 15:48:35 +00:00
Yukim1 205aa01c7b [Diffusion][HunyuanImage3] Add request paged prefix caching (#7719) 
Signed-off-by: zwhzzz0821 <2831474076@qq.com>
 2026-09-23 15:34:56 +00:00
MichaelCaoo 9a1a05facd [Bugfix][Core] Preserve static KV staging inputs in AR-Diffusion (#7921) 
Signed-off-by: MichaelCaoo <139663530+MichaelCao0@users.noreply.github.com>
 2026-09-23 23:17:45 +08:00
Weiming Liao 81bc7116c1 [NPU] upgrade to v0.30.0 (#8027) 
Signed-off-by: Weiming Liao <liaowm5@gmail.com>
 2026-09-23 14:59:29 +00:00
Wang fuyin d319d276f9 [Bugfix] Fix native Mooncake cross-stage KV layout mismatch (#8003) 
Signed-off-by: Acerak01-fy <wfy2003324@163.com>
 2026-09-23 14:57:45 +00:00
RyanYun09 732d6085be [CI][Omni-DuplexEval] Add nightly scoring CI guard (#7773) 
Signed-off-by: RyanYun09 <318555231+RyanYun09@users.noreply.github.com>
 2026-09-23 14:48:10 +00:00
Nick CaoandCodex d521b3f917 [Misc] remove legacy full_duplex alias for auto_response (#8024) 
Signed-off-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Codex <noreply@openai.com>
 2026-09-23 06:09:19 -07:00
Yuanheng Zhao 71125f80ad [New Model] Ming-Image (inclusionAI/Ming-Image-0.1-Design) Support (#8021) 
Signed-off-by: Yuanheng <jonathan.zhaoyh@gmail.com>
 2026-09-23 12:20:06 +00:00
Yuan WuandHongsheng Liu cb5f508212 [Feature] Transfer AR-to-diffusion payloads over NIXL (#6264) 
Signed-off-by: yuanwu <yuan.wu@intel.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-09-23 18:26:53 +08:00
Sy03 8953d082c0 [Bugfix] Fix Qwen3-TTS prefill probe on MRv2 runner (#8065) 
Signed-off-by: Sy03 <1370724210@qq.com>
 2026-09-23 10:17:53 +00:00
Dong1017 57d3e9fdf8 [BugFix][Diffusion] Scope Wan RMSNorm patch to NPU (#8047) 
Signed-off-by: GUOGUO <xwdong1998@163.com>
 2026-09-23 15:08:02 +08:00
wangyu 75570ee3a6 [CI/Build] Move Breeze-TTS-2 voice design e2e to weekly (#8032) 
Signed-off-by: wangyu <410167048@qq.com>
 2026-09-23 10:46:23 +08:00
Sy03 5634f03eb1 [Bugfix] Restore MRV2 full-payload transport for offline Qwen3-TTS (#8010) 
Signed-off-by: Sy03 <1370724210@qq.com>
 2026-09-23 01:51:20 +00:00
Yueqian Lin 3f473a358b [Model] Accelerate Breeze-TTS-2 non-streaming inference (#7752) 2026-09-22 17:10:15 -07:00
Sicheng Hua d2aa07159c [Bugfix][Qwen3-TTS] Ignore voice labels for inline Base cloning (#6974) 
Signed-off-by: sc-hua <sc_hua@qq.com>
 2026-09-22 16:19:37 -07:00
MaciejBalaNV 7d6e2ade6c [bugfix] Fix FP8 Quack kernels when using Context Parallelism and reduce number of recompilations (#7458) 
Signed-off-by: Maciej Bala <mbala@nvidia.com>
 2026-09-22 11:38:17 -07:00
MaciejBalaNV c482626450 [optimization] Added Wan 2.2 VAE decode optimizations (#7056) 
Signed-off-by: Maciej Bala <mbala@nvidia.com>
Signed-off-by: MaciejBalaNV <mbala@nvidia.com>
 2026-09-22 11:37:49 -07:00
Jiaqian Liu 7b6a5ee894 [Hardware][Ascend] Add opt-in chunked anti-alias FIR upsampling (#7896) 
Signed-off-by: Jiaqian Liu <591998922@qq.com>
 2026-09-22 10:24:01 -07:00
shiyichuanandmershi 8422887d9f [Bugfix] Merge audio final output into the matching text choice (#7376) (#7879) 
Signed-off-by: mershi <mershi@tencent.com>
Co-authored-by: mershi <mershi@tencent.com>
 2026-09-22 10:23:26 -07:00
Deep Shah b44cf97b31 [Bugfix] Preserve all video-stream audio deltas (#7532) 
Signed-off-by: Deep Shah <deep@socratic.co>
 2026-09-22 10:19:16 -07:00
Zhou TaichangClaude Opus 5Gao Han
 		59db6a4285 [Rebase] Rebase to vLLM 0.30.0 (#7820) 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
v0.30.0rc1 		2026-09-22 15:52:01 +00:00
yanbao1217andyanbao1217 ca14e635f5 [Doc] Correct the SessionClosed admission-slot guarantee (#7636 Issue 22) (#7869) 
Signed-off-by: yanbao1217 <yanliuwebsite493@gmail.com>
Co-authored-by: yanbao1217 <yanliuwebsite493@gmail.com>
 2026-09-22 14:57:50 +00:00
Sun d278aa8057 [Bugfix] Mark image edit benchmark stream errors as failed (#8015) 
Signed-off-by: levius <2114377220@qq.com>
 2026-09-22 14:56:30 +00:00
Si Chen f1057b1e0d [Bugfix] Restore GLM-Image unshifted timesteps after set_timesteps (#7953) 
Signed-off-by: sinksilk <785976238@qq.com>
 2026-09-22 13:45:55 +00:00
Sun 03ccce9a99 [Bugfix] Mark Omni chat benchmark streams with error events as failed (#8000) 
Signed-off-by: levius <2114377220@qq.com>
 2026-09-22 06:28:18 -07:00
Clodagh Walsh 7af2c3d351 [CI][Voxtral] Resolve failing test_prepare_speech_generation_awaits_voxtral_async (#7601) 
Signed-off-by: Clodagh Walsh <clodaghwalsh17@gmail.com>
 2026-09-22 06:07:35 -07:00
Yueqian Lin 3032b4a013 [CI] Bump the public env var snapshot count after #6848 landed (#7964) 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
 2026-09-22 08:38:08 -04:00
ZacheryAUandamy-why-3459 0582844a41 [Frontend][Benchmark] Add duplex performance metrics to refactored full-duplex framework (#7714) 
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-09-22 03:04:22 -07:00
Wang fuyin 9ebef4b1d3 [Feat] Add prefetch for Mooncake cross-stage paged KV transfer in HunyuanImage3 (#7637) 
Signed-off-by: Acerak01-fy <wfy2003324@163.com>
 2026-09-22 02:21:42 -07:00
vOv f7e28348ad [Bugfix] Stabilize NIXL manager receiver tests (#7984) 
Signed-off-by: cr-gao <gaochenrui@sjtu.edu.cn>
 2026-09-22 16:11:42 +08:00
vOv 939e6ba56e [CI/Build] Give diffusion CPU tests more timeout headroom (#7983) 
Signed-off-by: cr-gao <gaochenrui@sjtu.edu.cn>
 2026-09-22 15:47:00 +08:00
Tianyao Wu ba5b7485a7 [Bugfix] Keep resumable duplex prompts out of async-chunk prewarm (#7992) 
Signed-off-by: Tianyao Wu <rayroy31@gmail.com>
 2026-09-22 15:36:42 +08:00
Armaan Amatya f3f8ebfc25 [CI] Count VLLM_OMNI_SPEAKER_REGISTRATION_POLICY in the inventory snapshot (#7977) 
Signed-off-by: Armaan Amatya <armaanamatya2014@gmail.com>
 2026-09-22 05:45:23 +00:00
Sy03 c7cd37b61e [Model] Reduce MOSS TTS reference audio preparation overhead (#7725) 
Signed-off-by: Sy03 <1370724210@qq.com>
 2026-09-22 12:19:18 +08:00
汪志鹏 f8a00b1491 [Misc] Add portable MiniMax H3 skills (#7923) 
Signed-off-by: princepride <wangzhipeng628@gmail.com>
 2026-09-22 11:10:42 +08:00
Wang fuyin 303edff930 [Doc][skip ci] Add design doc for scheduler-managed diffusion paged KV cache (#6891) 
Signed-off-by: Acerak01-fy <wfy2003324@163.com>
 2026-09-22 10:53:37 +08:00
wangyu 0570b0da7e [CI][Perf] migrate diffusion DFX benches to vllm bench serve --omni (#7737) 
Signed-off-by: wangyu <410167048@qq.com>
 2026-09-21 19:16:39 -07:00
SworolSworolClaude Code
 		a4ad73e08b [Bugfix] Fix GLM-TTS DiT float32 crash with flash-attn backends (#7756) 
Signed-off-by: Sworol <171231900+Sworol@users.noreply.github.com>
Co-authored-by: Sworol <171231900+Sworol@users.noreply.github.com>
Co-authored-by: Claude Code <noreply@anthropic.com>
 2026-09-21 19:13:20 -07:00
akshatvishu 502a86fff7 [Core] Optimize Qwen2.5-Omni Token2Wav buffer loading (#7061) 
Signed-off-by: akshatvishu <akshatnayak197@gmail.com>
 2026-09-21 19:13:12 -07:00
liuyihua95 36cdeb8fda [Bugfix][TTS] Fix Audio8 voice clone reference resolution (#7815) 
Signed-off-by: liuyihua <i@liuyihua.com>
 2026-09-21 19:13:03 -07:00
jeffaa729 5152b9bf4c [Bugfix][Model] Fix CoVo-Audio prompt processing and dummy loading (#7909) 
Signed-off-by: jeffaa729 <hoiwanglo@gmail.com>
 2026-09-21 19:12:54 -07:00
Gawr Gura 0721 6d339671ed [Bugfix] Reject stray <|AUDIO|> placeholder with use_audio_in_video in Qwen2.5-Omni (#7959) 
Signed-off-by: RunguoLi <li19107254665@gmail.com>
 2026-09-21 19:12:46 -07:00