 Sy03
|
daf91b4d7a
|
Merge main and preserve multi-API engine and duplex guards
Signed-off-by: Sy03 <1370724210@qq.com>
|
2026-09-16 16:40:16 +08:00 |
|
|
y-nullandamy-why-3459
|
5f7f62e13c
|
[Bugfix][MiniCPM-o] Stabilize code2wav CFM CUDA graph caching with reference audio normalization and mel-frame bucketing (#7416)
Signed-off-by: y_null <y_null@qq.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
|
2026-09-16 01:24:31 -07:00 |
|
|
Sy03
|
40a000de05
|
Document multi-API serving tradeoffs in TTS profile
Signed-off-by: Sy03 <1370724210@qq.com>
|
2026-09-16 16:00:45 +08:00 |
|
|
SYLARandlishunyang12
|
507cb1d834
|
[Attention] [P1] Keep H3 VSA policy in the model and share sparse primitives (#7535)
Signed-off-by: lishunyang12 <lishunyang12@users.noreply.github.com>
Co-authored-by: lishunyang12 <lishunyang12@users.noreply.github.com>
|
2026-09-16 15:47:31 +08:00 |
|
|
chickeytonandClaude Opus 5
|
99ff4f3070
|
[Core][Frontend] Unified Full-duplex Framework (#7413)
Signed-off-by: chickeyton <ngton2014@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-16 15:35:36 +08:00 |
|
|
linzhenpl07andClaude Opus 5
|
9005d78903
|
[LingBot World] Reuse the text encode for a prompt already encoded (#6845)
Signed-off-by: linzhenpl07 <linzhenpl07@gmail.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-09-16 15:01:11 +08:00 |
|
|
Zhou Taichang
|
5e9024171d
|
[Bugfix] Skip generic text-only warmup for DreamZero (#7548)
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
|
2026-09-16 14:43:18 +08:00 |
|
|
vOv
|
21d86ec923
|
[Diffusion] MAGI-2: regional compile coverage (#7174)
Signed-off-by: cr-gao <gaochenrui@sjtu.edu.cn>
|
2026-09-16 13:01:26 +08:00 |
|
|
GXIN
|
a2138b830f
|
[Feature][Qwen3-TTS] Make Code2Wav honor the stage dtype (#6059)
Signed-off-by: XIN GAO <1037396230@qq.com>
|
2026-09-16 04:50:00 +00:00 |
|
|
Sy03
|
dc3c7dbe16
|
Rebase multi-API serving on latest main
Signed-off-by: Sy03 <1370724210@qq.com>
|
2026-09-16 12:13:04 +08:00 |
|
|
Zheng Wengangandwuli666
|
275720b378
|
[Bugfix] Keep async video jobs queued until inference and abort on delete (#6759)
Signed-off-by: ZhengWG <zwg0606@gmail.com>
Signed-off-by: wuli666 <421774554@qq.com>
Co-authored-by: wuli666 <421774554@qq.com>
|
2026-09-15 20:43:30 -07:00 |
|
|
Yueqian Lin
|
5dbae2b182
|
[Bugfix] Per-key accumulation strategy for Qwen3-TTS codec frame outputs (#7608)
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
|
2026-09-15 20:08:49 -07:00 |
|
|
psv666
|
7bceb1a76b
|
[Bugfix] Align video frame consumption reporting with prompt sampling (#7329)
|
2026-09-16 02:49:07 +00:00 |
|
|
HAAZZZEEEE
|
3eb5c3b4e6
|
[Bugfix][Wan2.2] Apply UniPC flow shift once (#7576)
Signed-off-by: HAAZZZEEEE <wang-taicheng@qq.com>
|
2026-09-16 10:06:41 +08:00 |
|
|
Deep Shah
|
c197cd2422
|
[Bugfix] Fix Qwen3-Omni streaming crops in mixed-length batches (#7340)
Signed-off-by: Deep Shah <deep@socratic.co>
|
2026-09-15 18:26:43 -07:00 |
|
|
Clodagh Walsh
|
a1a234a0b4
|
[Voxtral] Raise BadRequest for ref_audio (#7012)
Signed-off-by: Clodagh Walsh <clodaghwalsh17@gmail.com>
|
2026-09-15 18:26:08 -07:00 |
|
|
leo
|
45a3e77351
|
[Bugfix] Route Music3 float32 attention to SDPA (#7354)
Signed-off-by: liuyao0322 <yaoliu548926@gmail.com>
|
2026-09-15 18:08:06 -07:00 |
|
|
ChangXiong Denganddengchangxiong
|
f420cfcfbf
|
[NPU][CosyVoice3] Add CPU STFT fallback (#7520)
Signed-off-by: dengchangxiong <dengchangxiong1@huawei.com>
Co-authored-by: dengchangxiong <dengchangxiong1@huawei.com>
|
2026-09-15 18:06:41 -07:00 |
|
|
LOGO127
|
65693b30fb
|
[Bugfix][Core] Keep sample-rate snapshots bounded in delta output (#7448)
Signed-off-by: luozijian <luozijian0924@gmail.com>
|
2026-09-15 16:50:32 -07:00 |
|
|
yzhautouskay
|
6040bb97e2
|
[Perf][Cosmos3] Add SeaCache support for Cosmos3 (#6922)
Signed-off-by: Yuliya Zhautouskaya <yzhautouskay@nvidia.com>
|
2026-09-15 14:57:15 -07:00 |
|
|
Mengjie ZhaoandCursor
|
c17126c219
|
[Model] Add Gepard-1.0 OpenAI /v1/audio/speech serving (#7499)
Signed-off-by: Mengjie Zhao <zmj0129@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-09-15 14:56:51 -07:00 |
|
|
dongbo910220
|
952022c8ec
|
[Diffusion][Perf] Add Qwen-Image QK RoPE Triton path (#5931)
Signed-off-by: dongbo910220 <1275604947@qq.com>
|
2026-09-15 14:28:48 +00:00 |
|
|
wtz2333
|
a3dee6fdf5
|
[Lingbot World] Bound image condition storage and extend temporal RoPE (#6838)
Signed-off-by: wtz2333 <2955110911@qq.com>
|
2026-09-15 18:49:55 +08:00 |
|
|
Deep Shah
|
5761ad5516
|
[Bugfix] Restore the async PP sampled-token broadcast in the AR runner (#7393)
Signed-off-by: Deep Shah <deep@socratic.co>
|
2026-09-14 20:41:03 -07:00 |
|
|
Anjie HouandClaude Opus 5
|
85da943391
|
[Refactor][Diffusion] Complete generic backend plan consumption (#7313)
Signed-off-by: specture724 <specture724@gmail.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-09-15 08:40:04 +08:00 |
|
|
Yueqian Lin
|
5385dda4fe
|
[Bugfix] Use current OpenAI audio event names in duplex client metrics (#7541)
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
|
2026-09-15 08:19:21 +08:00 |
|
|
Alex Brooks
|
01f4479138
|
[Bugfix] Don't shutdown Engine on py_generator=True (#6334)
Signed-off-by: Alex Brooks <albrooks@redhat.com>
|
2026-09-14 18:33:38 -04:00 |
|
|
ZacheryAU
|
f062124ba4
|
[Frontend][Benchmark] Add duplex performance metrics for OmniInteract and Omni-DuplexEval benchmark (#7242)
|
2026-09-14 15:25:59 -07:00 |
|
|
Zhichao Zhang
|
27f0e8c1ea
|
[Bugfix][Qwen3-TTS] Gate async-chunk Code2Wav on non_streaming_mode (#4371) (#6898)
Signed-off-by: Zhichao Zhang <60429419+smartDream-chao@users.noreply.github.com>
|
2026-09-14 15:25:51 -07:00 |
|
|
Amanandbezdarnost
|
a22a7dd68f
|
[Model] Add VoxCPM2 startup LoRA adapter support (#7108)
Signed-off-by: bezdarnost <urumbekovaman@gmail.com>
Co-authored-by: bezdarnost <urumbekovaman@gmail.com>
|
2026-09-14 15:25:42 -07:00 |
|
|
Tianyao WuandClaude
|
1b7e854b05
|
[Bugfix][MiniCPM-o] Attach a unit's whole frame group and size the vision slot budget like Stage0 (#7271)
Signed-off-by: Tianyao Wu <rayroy31@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-09-14 15:25:34 -07:00 |
|
|
Yash Jain
|
5f50fc3daf
|
[Kernel] Fuse Ming streaming ISTFT overlap-add and normalization (#7338)
Signed-off-by: Yash Jain <yashjainjain1704@gmail.com>
|
2026-09-14 15:25:25 -07:00 |
|
|
yulun
|
8e088c7725
|
[Hardware][Ascend][Model] Support MOSS-TTS-Nano on Ascend A2 (#7192)
Signed-off-by: Big2Wheel <1404207590@qq.com>
|
2026-09-14 15:25:17 -07:00 |
|
|
kunkun
|
c68eadbbe0
|
[Performance] Optimize MammothModa2 AR → DiT hidden-state transfer (#7102)
Signed-off-by: kunkunblueberry <1833921874@qq.com>
Signed-off-by: kunkun <72174834+kunkunblueberry@users.noreply.github.com>
|
2026-09-14 15:25:08 -07:00 |
|
|
Ethan ZHUandZhu Shihao
|
9f85b3722e
|
[Model] Stop MiniCPM-o Thinker at TTS boundaries (#7463)
Signed-off-by: Zhu Shihao <zhushihao@bytedance.com>
Co-authored-by: Zhu Shihao <zhushihao@bytedance.com>
|
2026-09-14 15:25:00 -07:00 |
|
|
LOGO127
|
7ad51f0007
|
[Misc][HiggsAudioV3] Diagnose skipped reference audio substitution (#7098)
Signed-off-by: luozijian <luozijian0924@gmail.com>
|
2026-09-14 15:24:49 -07:00 |
|
|
yadongandtanyadong
|
731e36fb57
|
[Bugfix][Hardware][Ascend] Fix Qwen3-TTS code predictor dtype and nested graph replay (#6639)
Signed-off-by: tanyadong <2209931449@qq.com>
Signed-off-by: tanyadong <yadongtan666@gmail.com>
Co-authored-by: tanyadong <2209931449@qq.com>
|
2026-09-14 11:43:02 -07:00 |
|
|
Pujitha PaladuguandPujitha Paladugu
|
5f25d98652
|
[Bugfix] Allow Fish Speech phoneme-control tokens through normalize_fish_speech_text (#7043)
Signed-off-by: Pujitha Paladugu <10557236+pujitha24@users.noreply.github.com>
Co-authored-by: Pujitha Paladugu <10557236+pujitha24@users.noreply.github.com>
|
2026-09-14 10:02:39 -07:00 |
|
|
heyuanliu-intel
|
40f8e94400
|
[Model][MiniMax-H3] Multi-GPU serving fixes and layer-wise offload component selection (#7047)
Signed-off-by: heyuanliu-intel <heyuan.liu@intel.com>
|
2026-09-14 10:02:30 -07:00 |
|
|
Deep Shah
|
2f1a18e69f
|
[Bugfix][Qwen3-Omni] Fix synchronous Thinker pipeline parallelism (#7345)
Signed-off-by: Deep Shah <deep@socratic.co>
|
2026-09-14 10:02:21 -07:00 |
|
|
nodeeeeee
|
909b121e0a
|
[Qwen2.5-Omni] Avoid redundant embedding computation (#7477)
Signed-off-by: nodeeeeee <zhangkai.nodeee@gmail.com>
|
2026-09-14 10:02:11 -07:00 |
|
|
|
ea1a416a17
|
[Model] Add Breeze-TTS-2 two-stage AR TTS support (talker + codec, streaming) (#7084)
Signed-off-by: noname <liuzhiwei08@kuaishou.com>
Signed-off-by: noname <133508552+lzwnoname@users.noreply.github.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: noname <liuzhiwei08@kuaishou.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
|
2026-09-14 09:55:53 -07:00 |
|
|
bcsdhjew
|
e0c4f97f32
|
[Bugfix][Frontend] Preserve duplex chat audio format and duration (#7316)
Signed-off-by: Nolen Liang <nliang@nvidia.com>
|
2026-09-14 09:05:55 -07:00 |
|
|
Tai An
|
1b6cd282f0
|
fix(qwen-image): drop the shadowed dead _get_qwen_prompt_embeds duplicate (#7461)
Signed-off-by: Anai-Guo <antai12232931@outlook.com>
|
2026-09-14 13:48:51 +00:00 |
|
|
BeatSeat
|
3d793481a0
|
[Bugfix][MiniCPMO45] Return bare tensor in Thinker forward to fix repetition loop (#7497) (#7517)
Signed-off-by: BeatSeat <wendavid552@gmail.com>
|
2026-09-14 21:11:15 +08:00 |
|
|
psv666
|
446c2b5474
|
[Bugfix] Forward Qwen3-Omni streaming video sampling parameters (#7325)
Signed-off-by: psv666 <2693925048@qq.com>
|
2026-09-14 19:29:50 +08:00 |
|
|
jiahengxie
|
2cbfd3e93b
|
[Performance][MammothModa2] Enable and validate FP8 KV cache for AR stage (#7436)
Signed-off-by: JH <13716265422@139.com>
|
2026-09-14 00:47:39 -07:00 |
|
|
Oliver7th
|
767cc7977e
|
[Bugfix][NPU] Materialize causal mask in FlashAttention dense path (#7324)
Signed-off-by: Oliver7th <fangzhengyi@huawei.com>
|
2026-09-14 01:46:29 +00:00 |
|
|
|
8e738ce21b
|
[P0][RFC #3747] RL rollout serving: session management + world_model_env (#4770)
Signed-off-by: srinivas_oo7 <sklinkedin0120@gmail.com>
Co-authored-by: srinivas_oo7 <sklinkedin0120@gmail.com>
Co-authored-by: Zhou Taichang <tzhouam@connect.ust.hk>
|
2026-09-14 09:26:44 +08:00 |
|
|
|
e284d907b5
|
[Perf][Frontend] Chunk in-memory image file responses (#7459)
Signed-off-by: QI JIA <qi.jia@shengshu.ai>
Co-authored-by: QI JIA <qi.jia@shengshu.ai>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-09-13 20:33:10 +08:00 |
|