anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
3,038 Commits 235 Branches 31 Tags
ab2f2a3d658db5be5ec96a950da55cb74b48e7aa
Commit Graph
138 Commits
Author SHA1 Message Date
tzhouamandClaude Fable 5.1 33de5d8629 Merge vLLM-Omni v0.29.0rc1 into edge-infer/omni-0.29.0 
The pair for vLLM v0.29.0: rc1's docs pin vllm==0.29.0 and a static scan of
rc1's vllm.* imports against the v0.29.0 tree finds nothing missing, while
our 0.28-based tree needs seven modules v0.29.0 no longer has
(vllm.inputs.preprocess, entrypoints.launcher, openai.cli_args,
openai.engine.protocol, serve.utils.server_utils, layers.batch_invariant,
models.hunyuan_v1).

Ten files conflicted. Upstream's structure is the base everywhere; the
fork's features are re-attached to it:
- deploy_profile / apply_deploy_profile run before rc1's resolve_omni_config
  pops deploy_config (async_omni_engine, cli/serve); the deploy-profile
  selector and the resolve_model_config_path chain it needs stay in
  entrypoints/utils.py; stage_overrides takes rc1's dict type.
- config_factory keeps the lazy diffusion output-type import; the diffusion
  registry import in rc1's new config/resolver.py is made lazy for the same
  WP6 reason (TTS path must not load diffusion).
- requirements: our core/media split kept; rc1's transformers>=5.13 floor
  and kernels==0.16.1 applied in core.txt / media.txt.
- TTS: rc1's split_granularity and bounded seed plus our output_mode=
  codec_tokens, _SessionInbox cancel handling and codec DELTA accumulation;
  our private _conditioning_cache_salt is superseded by rc1's public
  tts_adapters/base.py::conditioning_cache_salt.
- stage_runtime: rc1's single ExitStack G2 path (lock released before READY)
  replaces our two-path block, with the four worker_phase names the init
  profiler consumes still emitted; _cpu_placed / host admission kept.

Not yet run against vLLM 0.29.0: the tests listed in the W6 record.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-18 09:57:20 +08:00
Zhou TaichangandClaude Opus 5 aff7d64948 [Rebase] Rebase to vLLM 0.29.0 (#7230) 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
 2026-09-10 12:08:28 +08:00
tzhouamandClaude Fable 5.1 c893b638ad [Edge][WP5] Accumulate per-step codec delta rows (DELTA mode delivers only the newest row) 
Measured after the DELTA fix: 53 engine outputs for 52 rows, but the client
still received everything at once because each per-step payload is the newest
row only and the row alignment treated it as a cumulative snapshot (one yield
at the first row, one at the end). accumulate_codec_rows folds delta rows and
the final consolidated matrix into one growing matrix; unit test drives the
generator with per-step deltas and asserts one yield per step.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-09 16:45:24 +08:00
tzhouamandClaude Fable 5.1 380e8022dd [Edge][WP5] Normalize DELTA-mode codec snapshots (list of cumulative code matrices) before row alignment 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-09 16:31:56 +08:00
tzhouamandClaude Fable 5.1 b22dabe270 [Edge][WP5] Keep DELTA outputs for talker-only (codec-token) deployments 
The speech path forced FINAL_ONLY for Qwen3-TTS deployments without async
chunks, so a talker-only server emitted one engine output per request and all
codec frames arrived at once (measured: 1 engine output per request, first
codes at output #1). A talker-only stage (final_output + latent) now keeps
DELTA outputs so codec frames stream per step.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-09 16:21:31 +08:00
tzhouamandClaude Fable 5.1 b8d1e44ebe [Edge][WP5] Codec stream diagnostics: per-request output/codes counters, client saves received codes, offline parity diag 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-09 16:02:02 +08:00
tzhouamandClaude Fable 5.1 49a839ecf9 [Edge][WP5] Add codec-token streaming mode with on-device decoding 
* qwen3_tts_talker_only pipeline (single terminal LLM_AR stage,
  final_output_type "latent") + vllm_omni/deploy/qwen3_tts_talker_only.yaml;
  a terminal talker publishes its per-step codes.audio rows to the client
  (omni_client_multimodal_output_keys).
* /v1/audio/speech/stream: session.config.output_mode="codec_tokens" streams
  codec.start (JSON) + binary frames (<IHB seq/n_frames/flags + int16 rows,
  vllm_omni/entrypoints/openai/codec_stream.py) + codec.done; new input.cancel
  message aborts an in-flight generation for both codec and PCM sessions
  (single reader task + session inbox replaces direct socket reads); optional
  session.config.seed; audio.done gains "cancelled" only when it happened.
* serving_speech._generate_codec_chunks aligns the cumulative code tensor to
  output token ids (drops prefill placeholder/EOS rows) and emits deltas.
* TTS adapters: supports_codec_stream / codec_stream_spec (Qwen3-TTS: 16
  codebooks, 2048 ids, 12.5 Hz, 24 kHz, decoder qwen3_tts_tokenizer_v2_12hz).
* examples/online_serving/text_to_speech/qwen3_tts/edge_decoder_client.py
  decodes locally with Qwen3TTSTokenizerV2Decoder (ramp schedule, 72-frame
  context, cancel/reset), codec_parity_check.py and
  benchmarks/tts/codec_stream_e2e.py compare against the two-stage server.
* docs/serving/codec_token_streaming.md; CPU unit tests for the wire format,
  alignment, session config and handler (frames, unsupported adapter, cancel);
  L3 e2e tests/e2e/online_serving/test_qwen3_tts_codec_stream.py.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-09 11:10:13 +08:00
NancyFyongandNancyFyong e74fe3c6e8 [Model] Add Audio8 TTS Preview 0.6B (DualAR, 44.1 kHz codec) (#6157) 
Signed-off-by: NancyFyong <NancyFyong@users.noreply.github.com>
Co-authored-by: NancyFyong <NancyFyong@users.noreply.github.com>
 2026-09-08 19:00:25 -07:00
boatman cdf027874c [Feat][OmniVoice]Support Varlen Attn, Request-Batch and Step-Execution (#6408) 
Signed-off-by: boatman <109857087+sphinxkkkbc@users.noreply.github.com>
 2026-09-08 18:58:38 -07:00
boatman 043f03d576 [Migrate]Move model-specific helpers out of serving_speech (#6697) 
Signed-off-by: boatman <109857087+sphinxkkkbc@users.noreply.github.com>
 2026-09-08 08:59:45 +08:00
BruceLoveDecimalandClaude Opus 5 1e74807c35 [Feature][Moss-TTS] Reference Audio Preprocessing (#4982) 
Signed-off-by: BruceLoveDecimal <39156883+BruceLoveDecimal@users.noreply.github.com>
Signed-off-by: liuqihao <liuqihao970610@gmail.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
 2026-09-04 16:36:26 -07:00
LOGO127 b6b992ac7b [Bugfix] Fix Higgs Audio v3 voice-clone token validation (#7065) 
Signed-off-by: luozijian <luozijian0924@gmail.com>
 2026-09-04 16:06:47 -07:00
AuFlowandHongsheng Liu 49c6fc1540 [Frontend] Add configurable output sample rate to Speech API (#6553) 
Signed-off-by: 郑倩倩 <2458983186@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-09-01 17:25:09 +08:00
Sy03 3adee400a0 [Bugfix][Qwen3-TTS] Handle codec generations that exhaust their token budget (#6728) 
Signed-off-by: Sy03 <1370724210@qq.com>
 2026-08-29 08:59:05 -07:00
Honghan Zhu f584729f24 [BugFix] Fix local media access for diffusion speech (#6622) 
Signed-off-by: zhuhh97 <zhuhonghan@huawei.com>
 2026-08-29 02:01:24 +00:00
Pranav ThakurandZhou Taichang 53b60bd9bc [Bugfix] Invalidate stale ref_audio cache on local file modification (#4873) (#5670) 
Signed-off-by: pranavthakur0-0 <pranavthakurdew@gmail.com>
Co-authored-by: Zhou Taichang <tzhouam@connect.ust.hk>
 2026-08-25 10:06:32 +08:00
boatmanandHongsheng Liu 3781214675 [Refactor] Move model-specific capability metadata into TTS adapters (#6138) 
Signed-off-by: boatman <109857087+sphinxkkkbc@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-08-22 14:26:49 +08:00
Doug Smith 07ceb3324a [BugFix][TTS] Move user input from INFO to DEBUG in TTS/audio log lines (#6329) 2026-08-18 16:22:11 -06:00
JackyLiuandHongsheng Liu d7216ef514 Add speech token usage headers (#4499) 
Signed-off-by: JackyLiu <lzwgre@126.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-08-18 06:53:06 +08:00
boatman 65b3d41b3a [Migrate] Move sampling parameter overrides from legacy dispatches to TTS adapters (#5272) 
Signed-off-by: boatman <109857087+sphinxkkkbc@users.noreply.github.com>
 2026-08-16 21:14:26 -07:00
Alex Brooks fe54ecc388 [Frontend] Loosen Validation for TTS Models with No Uploaded Speakers (#5878) 
Signed-off-by: Alex Brooks <albrooks@redhat.com>
 2026-08-14 17:05:11 -06:00
Zhenghan Song 72a02b492a [Bugfix] Fix diffusion TTS adapter lookup in speech serving (#6121) 
Signed-off-by: HaningZS <resossr0v0@gmail.com>
 2026-08-12 15:20:12 -04:00
Shi Boao Bowie汪志鹏ruirui yangamy-why-3459Gao HanHongsheng Liu
 		fcf1085395 [Refactor][OutputProcessor 2/8]: OmniRequestOutput should inherit RequestOutput and no nested wrap-up (#5146) 
Signed-off-by: Boao Shi <aoibosh@connect.hku.hk>
Signed-off-by: bowieshi <aoibosh@connect.hku.hk>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: R2-Y <ruiruyang2@gmail.com>
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
Signed-off-by: Shi Boao Bowie <aoibosh@connect.hku.hk>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: ruirui(rein) yang <73573651+R2-Y@users.noreply.github.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-08-12 22:58:23 +08:00
王金旭xuruiClaude Opus 4.8
 		9b0df3909a [Feature] timestamps for TTS via a forced-aligner pooling (#4795) 
Signed-off-by: wjinxu <1299461899@qq.com>
Co-authored-by: xurui <xurui1@modelbest.onaliyun.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-08-12 05:33:34 +00:00
Sy03andYueqian Lin 58007c0084 [New Model] Support IndexTTS 2.5 (#5957) 
Signed-off-by: Sysy <1370724210@qq.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
 2026-08-11 23:00:35 +00:00
boatman 11f633aa83 [Refactor] Add Ming Flash Omni TTS adapter (#5746) 
Signed-off-by: boatman <109857087+sphinxkkkbc@users.noreply.github.com>
 2026-08-10 01:47:09 +00:00
Yueqian Lin ebe93f5d1e [Refactor][TTS] Derive TTS model detection from adapter metadata (#5682) 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
 2026-08-09 21:30:05 +08:00
Sy03 09c6ad4204 [CI/Build][MiniCPM-o] Allow auto-response before input commit (#5567) 
Signed-off-by: Sy03 <1370724210@qq.com>
 2026-07-30 14:14:19 +00:00
Canlin Guo 18be2ba3df [Perf] Enable compile for MOSS-TTS-Local v1.5 talker and codec (#5530) 
Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>
 2026-07-29 14:09:06 +08:00
Yuekai ZhangClaude Fable 5Yueqian LinYueqian Lin
 		5014fea4a0 [New Model] support nemotron Audex (#4976) 
Signed-off-by: Yuekai Zhang <zhangyuekai@foxmail.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
 2026-07-28 03:58:22 +00:00
LHXuuuandYuanheng Zhao fb89ab43ea [Refactor][Ming-TTS] Move speaker extraction and caching to Stage-0 (#5351) 
Signed-off-by: LHXuuu <xulianhao.xlh@antgroup.com>
Co-authored-by: Yuanheng Zhao <54058983+yuanheng-zhao@users.noreply.github.com>
 2026-07-27 07:55:47 -07:00
boatman 76e4a78afc [Bugfix][Higgs-Audio-V3] Propagate Sampling Parameters to Sampler (#5406) 
Signed-off-by: boatman <109857087+sphinxkkkbc@users.noreply.github.com>
 2026-07-25 15:25:35 +00:00
LHXuuu 00bdb5dcd7 [Perf][Ming-TTS] Cache speaker embeddings for uploaded reference audio (#5240) 
Signed-off-by: LHXuuu <xulianhao.xlh@antgroup.com>
 2026-07-23 11:22:51 +08:00
Shenglei Fu 7b2edd6650 [Bugfix][Qwen3-TTS] Mode-aware ref_audio artifact readiness (fixes #5049) (#5157) 2026-07-20 00:38:07 -07:00
boatmanandYueqian Lin 32dddfcef4 [Cleanup]Migrate model validation to adapters and clean up serving_speech.py (#4833) 
Signed-off-by: boatman <109857087+sphinxkkkbc@users.noreply.github.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
 2026-07-19 23:03:32 -07:00
Zhou TaichangandClaude Opus 4.8 d3c47efc4f [Rebase] Rebase to vllm v0.25.0 (#5042) 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-07-12 23:39:53 +08:00
LHXuuu 5c3923509d [BugFix][Ming-TTS] Use uploaded direct speaker embeddings by voice (#5005) 
Signed-off-by: LHXuuu <xulianhao.xlh@antgroup.com>
 2026-07-10 07:06:18 +00:00
Sy03andYueqian Lin 1b31f96240 [Bugfix] Fix Qwen3-TTS no-async-chunk payload splitting (#4870) 
Signed-off-by: Sy03 <1370724210@qq.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
 2026-07-04 19:57:55 +00:00
Sy03andYueqian Lin 0798b0bf03 [Bugfix][Qwen3-TTS] Seed residual MTP sampling (#4869) 
Signed-off-by: Sy03 <1370724210@qq.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
 2026-07-04 17:47:11 +00:00
boatman 29dcdec66d [Cleanup]Replace legacy logging branches with PreparedRequest.model_type (#4862) 
Signed-off-by: boatman <109857087+sphinxkkkbc@users.noreply.github.com>
 2026-07-04 05:39:20 +00:00
LHXuuu 991fb7408b [BugFix][Ming-TTS] Improve Seed-TTS WER accuracy (#4859) 
Signed-off-by: LHXuuu <xulianhao.xlh@antgroup.com>
 2026-07-03 12:15:03 +02:00
Canlin Guo a8b2bf11d2 [Feature] Support MOSS-TTS-Local-v1.5 Streaming (#4804) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
 2026-07-03 16:00:30 +08:00
faceless void 11f6a0b72e Make speech streaming default to SSE (#4679) 
Signed-off-by: syd520zy <529477025@qq.com>
 2026-06-30 02:17:24 +00:00
Yueqian Lin 92f7208559 [Bugfix] CosyVoice3: wrap ref_text in instruction template (#4644) (#4756) 2026-06-27 14:38:33 -07:00
Yueqian LinandSy03 b66cd024b9 [Bugfix] Fix /v1/audio/speech usage token accounting for Qwen3-TTS (#4646) (#4673) 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Sy03 <1370724210@qq.com>
 2026-06-27 06:13:31 +08:00
LHXuuuYuanheng ZhaoYuanheng ZhaoHongsheng Liu
 		0b04f2a0d6 [Model] Add Ming-omni-tts MoE 16.8B-A3B + CFM CUDAGraph (#4341) 
Signed-off-by: LHXuuu <xulianhao.xlh@antgroup.com>
Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com>
Co-authored-by: Yuanheng Zhao <54058983+yuanheng-zhao@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-06-25 22:11:35 +08:00
Canlin Guo 2e6c83c89c [Model] Support MOSS-TTS-local-v1.5 (#4664) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
 2026-06-25 15:43:03 +08:00
BeatSeat 044240d8eb [Model] Add IndexTTS2 text-to-speech support (#3838) 
Signed-off-by: BeatSeat <wendavid552@gmail.com>
Signed-off-by: David <david@podcast.ai>
Signed-off-by: wendavid552 <wendavid552@gmail.com>
Signed-off-by: WenDavid <davidzhangcf@foxmail.com>
 2026-06-22 19:24:01 +00:00
+2
faceless voidNick CaoChendi.XueHongsheng LiuKristofferJunhong LiulishunyangCopilot Autofix powered by AIHyoseop SongZhou TaichangAliciaamy-why-3459
 		ec4ec0f604 Add SSE stream_format support for audio speech streaming (#4490) 
Signed-off-by: syd520zy <529477025@qq.com>
Signed-off-by: faceless void <100186390+syd520zy@users.noreply.github.com>
Signed-off-by: Nick Cao <ncao@redhat.com>
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Signed-off-by: kTorp <Kristoffer.Torp@amd.com>
Signed-off-by: Junhong Liu <98734602+LJH-LBJ@users.noreply.github.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Signed-off-by: Hyoseop Song <crad_on25@naver.com>
Signed-off-by: Hyoseop Song  <crad_on25@naver.com>
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Chendi.Xue <chendi.xue@intel.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Kristoffer <kristoffer.torp@amd.com>
Co-authored-by: Junhong Liu <ljh_lbj@163.com>
Co-authored-by: lishunyang <lishunyang12@163.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Hyoseop Song <crad_on25@naver.com>
Co-authored-by: Zhou Taichang <tzhouam@connect.ust.hk>
Co-authored-by: Alicia <115451386+congw729@users.noreply.github.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-06-22 06:42:25 +00:00
王金旭CursorClaude Opus 4.8
 		ad07f98b73 [Feat] Streaming TTS word-level timestamps via forced aligner (#4034) 
Signed-off-by: wjinxu <1299461899@qq.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-22 04:51:45 +00:00