vllm-omni

audio8_tts

[Model] Add Audio8 TTS Preview 0.6B (DualAR, 44.1 kHz codec) (#6157 )

2026-09-08 19:00:25 -07:00

aura_omni/duplex

[Model] Integrate AURA into Full-Duplex Runtime (#7633 )

2026-09-21 09:26:54 -07:00

common

[Model] Optimize Qwen3-Omni MRv2 handoff, code prediction and audio decoding (#8223 )

2026-10-01 22:22:54 -07:00

cosyvoice3

[Model] Optimize CosyVoice3 packed streaming with bounded HiFT graphs (#8420 )

2026-10-02 08:49:50 -07:00

fish_speech

[Bugfix] Isolate weekly CPU tests from inherited attention env and hf_api mocks (#7565 )

2026-09-21 15:55:00 +00:00

glm_image

[Rebase] Rebase to vLLM 0.29.0 (#7230 )

2026-09-10 12:08:28 +08:00

higgs_audio_v3

[Bugfix] Initialize eager state in Higgs test fixture (#8426 )

2026-10-02 10:22:52 -04:00

indextts2

[Bugfix] Fix the remaining Python 3.10 breakages (#7985 )

2026-09-30 11:38:23 +08:00

mammoth_moda2

[Bugfix][MammothModa2] Stop allocating AR KV cache for the replaced language model (#8095 )

2026-09-25 21:28:59 +08:00

mimo_audio

[Bugfix][MiMo-Audio] Align code2wav decode with tokenizer device (#6539 )

2026-09-08 18:38:11 -07:00

ming_flash_omni

[Refactor] Replace and ban a few torch.cuda functions in favor of torch.accelerator replacements. (#3365 )

2026-05-07 23:23:59 +08:00

ming_image

[Bugfix] Align Ming-Image prompt templates and RNG, fix number of layer to decompose (#8118 )

2026-09-25 22:47:29 +08:00

ming_tts

[Kernel] Fuse Ming streaming ISTFT overlap-add and normalization (#7338 )

2026-09-14 15:25:25 -07:00

minicpmo_4_5

[Bugfix] Defer VoxCPM2 NPU patch to avoid platform import cycle (#8330 )

2026-09-30 05:25:36 -07:00

moss_tts

[CI/Build] Fix MOSS CPU tests on ROCm workers (#8447 )

2026-10-03 09:13:51 +08:00

moss_tts_nano

[Hardware][Ascend][Model] Support MOSS-TTS-Nano on Ascend A2 (#7192 )

2026-09-14 15:25:17 -07:00

nemotron_voicechat

[Bugfix] Fix Nemotron VoiceChat duplex nightly handshake (#7884 )

2026-09-25 17:25:15 +00:00

omnivoice

rebase: align vllm-omni with vLLM ac9126e58aa7

2026-10-02 10:37:50 +08:00

personaplex

[Perf][PersonaPlex] Serve 16 concurrent realtime duplex sessions on one GPU (#8192 )

2026-09-28 04:51:38 +00:00

qwen2_5_omni

rebase: align vllm-omni with vLLM ac9126e58aa7

2026-10-02 10:37:50 +08:00

qwen3_omni

[Model] Optimize Qwen3-Omni MRv2 handoff, code prediction and audio decoding (#8223 )

2026-10-01 22:22:54 -07:00

qwen3_tts

[Model] Add single-stage Qwen3-TTS with in-Talker streaming codec decode (#8259 )

2026-10-02 21:34:30 +10:00

step_audio2

[Bugfix][TTS] Isolate concurrent StepAudio2 TRT builds (#6957 )

2026-09-02 19:53:02 +00:00

voxcpm2

[Model] Make VoxCPM2 generation settings configurable (#7010 )

2026-09-30 11:26:12 +08:00

voxtral_tts

[CI]Split GPU jobs by cards_* and reject hand-written SKU marks (#6650 )

2026-08-29 18:42:33 +08:00

breeze_tts_2_helpers.py

[Model] Accelerate Breeze-TTS-2 non-streaming inference (#7752 )

2026-09-22 17:10:15 -07:00

registry.py

[Bugfix] Fix omni processing test for non-multimodal talker stage (#3559 )

2026-05-13 10:08:23 +08:00

test_aura_qwen3_vl.py

[Model] Aura support - Non async chunk path (#4257 )

2026-06-21 22:08:26 +08:00

test_breeze_tts_2_first_code_integration.py

[Model] Accelerate Breeze-TTS-2 non-streaming inference (#7752 )

2026-09-22 17:10:15 -07:00

test_breeze_tts_2_first_code_sampler.py

fix: repair ROCm test routing, CPU timeouts, and Breeze autotuning (#8342 )

2026-10-02 07:36:41 +08:00

test_breeze_tts_2_graphs.py

fix: repair ROCm test routing, CPU timeouts, and Breeze autotuning (#8342 )

2026-10-02 07:36:41 +08:00

test_breeze_tts_2_preprocess.py

[Model] Accelerate Breeze-TTS-2 non-streaming inference (#7752 )

2026-09-22 17:10:15 -07:00

test_breeze_tts_2_registration.py

[Model] Accelerate Breeze-TTS-2 non-streaming inference (#7752 )

2026-09-22 17:10:15 -07:00

test_breeze_tts_2_sampling_eos.py

[Model] Accelerate Breeze-TTS-2 non-streaming inference (#7752 )

2026-09-22 17:10:15 -07:00

test_breeze_tts_2.py

[Model] Accelerate Breeze-TTS-2 non-streaming inference (#7752 )

2026-09-22 17:10:15 -07:00

test_encoder_quant_config.py

[diffusion][feature] Add offline SVDQuant W4A4 support (#6162 )

2026-08-27 08:45:53 +08:00

test_gepard_window.py

[Model] Add Gepard-1.0 native-AR FSQ/NanoCodec TTS (offline inference) (#5666 )

2026-08-14 22:06:05 -07:00

test_gepard_wiring.py

[Refactor] Worker/ModelRunner runner correctness fixes (G2/N) (#5452 )

2026-08-20 16:47:50 +08:00

test_glm_tts_dit_attention.py

[Bugfix] Fix GLM-TTS DiT float32 crash with flash-attn backends (#7756 )

2026-09-21 19:13:20 -07:00

test_glm_tts_prompt_len.py

[Model] Add GLM-TTS text-to-speech model support (#3141 )

2026-05-24 05:42:26 +08:00

test_kv_cache_scale_mapper.py

[Bugfix] Fix Hunyuan Image-3 expert mapping contract (#7021 )

2026-09-06 21:43:37 +08:00

test_minimax_h3_encoder_payload.py

[Feature] Transfer AR-to-diffusion payloads over NIXL (#6264 )

2026-09-23 18:26:53 +08:00

test_minimax_h3_token_tags.py

[Model] MiniMax-H3: validate versioned text-conditioning handoff (#6720 )

2026-09-06 21:45:10 +08:00

test_minimax_music3_batch_payload.py

[Model] Add MiniMax Music 3 text-to-music (#6186 )

2026-08-18 04:33:13 +00:00

test_minimax_music3_dit_attention.py

[Bugfix] Route Music3 float32 attention to SDPA (#7354 )

2026-09-15 18:08:06 -07:00

test_minimax_music3_frame_state.py

[Model] Add MiniMax Music 3 text-to-music (#6186 )

2026-08-18 04:33:13 +00:00

test_minimax_music3_prompt.py

[Model] Add MiniMax Music 3 text-to-music (#6186 )

2026-08-18 04:33:13 +00:00

test_minimax_music3_repo_root.py

[Bugfix] Isolate weekly CPU tests from inherited attention env and hf_api mocks (#7565 )

2026-09-21 15:55:00 +00:00

test_minimax_music3_row_binding.py

[Model] Add MiniMax Music 3 text-to-music (#6186 )

2026-08-18 04:33:13 +00:00

test_model_local_kv.py

[Refactor] Declare model-local KV held outside the paged manager (#6171 )

2026-09-11 08:44:32 +08:00

test_nemotron_voicechat_perception_window.py

[Perf][NemotronVoiceChat] Fast defaults for all three deploy profiles: 2.8x offline, realtime full-duplex audio (#6354 )

2026-09-03 18:49:19 -07:00

test_nemotron_voicechat_registration.py

[Core] Validate PipelineConfig in __post_init__ (#6829 )

2026-09-01 11:17:57 +08:00

test_nemotron_voicechat_shapes.py

[Perf][NemotronVoiceChat] Fast defaults for all three deploy profiles: 2.8x offline, realtime full-duplex audio (#6354 )

2026-09-03 18:49:19 -07:00

test_nemotron_voicechat_talker_replay.py

[Perf][NemotronVoiceChat] Fast defaults for all three deploy profiles: 2.8x offline, realtime full-duplex audio (#6354 )

2026-09-03 18:49:19 -07:00

test_omni_processing.py

rebase: align vllm-omni with vLLM ac9126e58aa7

2026-10-02 10:37:50 +08:00

test_talker_first_audio.py

[Model] Optimize Qwen3-Omni MRv2 handoff, code prediction and audio decoding (#8223 )

2026-10-01 22:22:54 -07:00

test_weight_loader.py

[Rebase] Rebase to vLLM 0.29.0 (#7230 )

2026-09-10 12:08:28 +08:00