Commit Graph
18 Commits
Author SHA1 Message Date
tzhouamandClaude Fable 5.1 a58825ed6c perf(omnivoice): tokenize the prompt once per request
apply() already tokenized the prompt to build the engine prompt ids, but the
shared OmniMultiModalProcessor._apply_hf_processor_main then called
_call_hf_processor again, which rebuilt the control-token prompt and ran the
text tokenizer a second time before encoding the reference audio. Upstream's
_cached_apply_hf_processor invokes _apply_hf_processor_main for every
request, so this also happened for text-only requests and for requests whose
reference audio was already cached.

Split the old _call_hf_processor into _encode_prompt_text (used once, in
apply) and _encode_reference_audio, and override _apply_hf_processor_main to
encode the reference audio only, returning just the passthrough data when
there is no audio. _get_mm_fields_config registers only ref_audio_tokens and
ref_audio_len, so dropping input_ids from the media result changes no
consumer. The now-unreferenced _call_hf_processor is deleted; the prompt-text
kwarg transport is left as is.

Validation: ruff and pre-commit on both files; the module imports cleanly;
new tests/model_executor/models/omnivoice/test_processor_prompt_tokenization.py
covers text-only apply (one tokenizer call), the audio path (audio encoded,
no re-tokenization) and the empty-items path (no tokenizer, no encoder);
tests/model_executor/models/omnivoice (106), tests/inputs/test_mm_processor.py
and tests/entrypoints/openai_api/test_tts_{adapter,detection}.py (162) pass.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpXe2LeRrUQGjZfKFaocMZ
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
2026-09-10 00:41:53 +08:00
tzhouamandClaude Fable 5.1 188d021023 refactor(processors): drop _hf_processor_applies_updates overrides removed in vLLM 0.29
vLLM 0.29 deleted BaseMultiModalProcessor._hf_processor_applies_updates; no
reference to the hook remains anywhere in vllm/, so these six overrides were
never called. Delete them. No behaviour change.

Validation: pre-commit on the six files; CPU tests in tests/inputs and
tests/model_executor/models/{cosyvoice3,mimo_audio,step_audio2,omnivoice},
test_glm_tts_prompt_len.py and test_upstream_prompt_update_api.py pass;
the six processor modules import cleanly.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpXe2LeRrUQGjZfKFaocMZ
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
2026-09-10 00:41:53 +08:00
tzhouam efda9369a8 refactor: reduce copied vLLM 0.29 compatibility code
Reuse upstream weight mapping and multimodal processing, consolidate Omni processor bridges, and trim unused Hunyuan internals. Route no-media kwargs through the active renderer and preserve GLM generation prompt formatting.

Validation: 453 CPU tests passed, 7 skipped; processor imports, Ruff, and diff checks passed. GPU and end-to-end CI not rerun.
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
2026-09-10 00:41:53 +08:00
tzhouam 87a1fd8da2 rebase: adapt to vLLM v0.29 APIs
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
2026-09-10 00:41:52 +08:00
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
fdaf4e31bd Add vLLM-Omni library info to Hugging Face Hub requests (#5381)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-08 10:08:38 -06:00
DanaerLee ca6b4e2112 [Perf][Bugfix][OmniVoice] Restore float16 serving, and fuse the generator hot loop (#6317)
Signed-off-by: MrlixiangWE <mrdanaer@gmail.com>
2026-09-02 19:54:55 +00:00
Juan Pablo ZuluagaandYueqian Lin 5358f5db01 [Perf][TTS] omnivoice hot path: D2H batching, mask caching, cached text embeddings (#5174)
Signed-off-by: JuanPZuluaga <juanz9312@gmail.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
2026-08-12 17:15:35 +00:00
Yukim1andHongsheng Liu 793d3e9ab7 [Config] Return VllmOmniConfig from create_from_model (#4818)
Signed-off-by: zwhzzz0821 <2831474076@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-07-18 09:21:07 +00:00
Yukim1andAdvik 460a5c6b48 [Refactor] Migrate MammothModa2 and OmniVoice to pipeline registry (#4647)
Signed-off-by: Advik <scince5678@gmail.com>
Signed-off-by: Nightwing-77 <scince5678@gmail.com>
Signed-off-by: zwhzzz0821 <2831474076@qq.com>
Co-authored-by: Advik <scince5678@gmail.com>
2026-07-08 00:44:33 +00:00
Nick Cao 67d14b5ac4 [Refactor] Replace hardcoded CUDA device selection with platform-agnostic API (#4496)
Signed-off-by: Nick Cao <ncao@redhat.com>
2026-06-23 14:38:32 +08:00
Yueqian Lin 208932210f [Chore][TTS] Reference recipes.vllm.ai recipes, remove dead code, and fix stale references (#4567)
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
2026-06-19 15:05:26 +08:00
boatmanandsphinxkkkbc 4d9262a6eb [Feat]Support voice clone for omnivoice in online serving & add seed parameter for reproducible (#3668)
Signed-off-by: sphinxkkkbc <binchengkang8@gmail.com>
Co-authored-by: sphinxkkkbc <binchengkang8@gmail.com>
2026-05-29 07:42:08 +00:00
e7644daa7f [Perf] [OmniVoice] Triton kernel fusion + CUDA Graph acceleration (#3336)
Signed-off-by: univa-HARRY <harry@univa.co.kr>
Signed-off-by: Harry <harry@univa.co.kr>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
2026-05-22 13:12:47 +00:00
Yuanheng Zhao a64ebf103b [Refactor] Migrate and clean up TTS configs: CosyVoice3, OmniVoice, VoxCPM (#3338)
Signed-off-by: yuanheng <jonathan.zhaoyh@gmail.com>
Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com>
2026-05-17 07:32:34 +08:00
Zhou TaichangandYuanheng Zhao 7f2b1e9386 [Rebase] Rebase to vllm 0.20.0 (#3232)
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com>
Co-authored-by: Yuanheng Zhao <54058983+yuanheng-zhao@users.noreply.github.com>
2026-04-30 09:56:59 +12:00
Juan Pablo Zuluaga f7e8df9dbd [TTS][OmniVoice] Add voice cloning support for OmniVoice TTS (#2676)
Signed-off-by: JuanPZuluaga <juanz9312@gmail.com>
2026-04-11 12:14:03 -04:00
Yueqian Lin 0e83ebe1d4 [OmniVoice] Add two-stage TTS serving support (#2463)
Signed-off-by: linyueqian <linyueqian@outlook.com>
2026-04-03 20:41:20 +00:00