Commit Graph
3242 Commits
Author SHA1 Message Date
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
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
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
NATURE c1bfd60e43 [Frontend] Remove obsolete experimental duplex client parameters (#7647)
Signed-off-by: natureofnature <wzliu@connect.hku.hk>
2026-09-21 19:12:36 -07:00
Hoseung KimandHoseung Kim d4570afabf [Frontend] Reject built-in name collisions in voice upload and add VLLM_OMNI_SPEAKER_REGISTRATION_POLICY (#6848)
Signed-off-by: Hoseung Kim <hoseung.kim@navercorp.com>
Co-authored-by: Hoseung Kim <hoseung.kim@navercorp.com>
2026-09-21 18:35:07 -07:00
085cf0ff34 [Bugfix] Catch asyncio.TimeoutError so duplex serving starts on Python 3.10 (#7412)
Signed-off-by: Tianyao Wu <rayroy31@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Alicia <115451386+congw729@users.noreply.github.com>
2026-09-21 18:34:58 -07:00
Nick CaoandCodex 1d3dc8bf83 [Misc] Refactor static stage metadata lookups (#7602)
Signed-off-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Codex <noreply@openai.com>
2026-09-21 18:34:50 -07:00
andyluo7 1586c41ae4 [CI][ROCm] Shorten the blocking CosyVoice test path (#7748)
Signed-off-by: andyluo7 <andy.luo@amd.com>
2026-09-21 18:34:40 -07:00
Armaan Amatya cb31e0774f [Misc] Deprecate VLLM_OMNI_VOXCPM_CODE_PATH (#7779)
Signed-off-by: Armaan Amatya <armaanamatya2014@gmail.com>
2026-09-21 18:34:31 -07:00
0z5aand0z5a 8bc0c38b90 [Bugfix] Add opt-in MiniCPM-o 4.5 Stage-0 sliding window (#7631)
Signed-off-by: 0z5a <dezhen.lu@student.uni-tuebingen.de>
Signed-off-by: 0z5a <dezhen.lu@uni-tuebingen.de>
Co-authored-by: 0z5a <dezhen.lu@uni-tuebingen.de>
2026-09-21 18:34:22 -07:00
shihongzhi c11596c637 [Model] MammothModa2: enable Cache-DiT acceleration for the DiT stage (#7291)
Signed-off-by: shihongzhi <shi65881583@gmail.com>
2026-09-21 18:34:12 -07:00
jingchengtian 0b5f8832b9 [tts][feature][NPU] Add 2-NPU and 3-NPU disaggregated deploy profiles for MOSS-TTS-Local (#7052)
Signed-off-by: jingchengtian <tjc1995@126.com>
2026-09-21 23:14:52 +00:00
Sun 381b12fa87 [Bugfix] Keep --no-guardrails out of diffusion stage config (#7917)
Signed-off-by: levius <2114377220@qq.com>
2026-09-21 19:18:30 +00:00
Sy03 473da2cf82 [Perf][Qwen3-TTS] Enable event-driven orchestration by default (#7088)
Signed-off-by: Sy03 <1370724210@qq.com>
2026-09-21 12:09:19 -07:00