tzhouam 008fa25263 Merge main into dev/vllm-align for vLLM 0.31 release ...

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

2026-10-03 21:05:17 +08:00

..

ming

fix(ming): build ISTFT spectrogram in float32 (#7538)

2026-10-01 22:45:09 +00:00

ops

[Perf][Hunyuan] Optimize for vae and patch_embed (#6306)

2026-08-20 16:29:21 +00:00

__init__.py

[Feat][Qwen3-Omni] Shared code predictor module for Qwen3-TTS and Qwen3-Omni (#2375)

2026-04-15 15:14:57 +08:00

alias_free_activation.py

[Hardware][Ascend] Add opt-in chunked anti-alias FIR upsampling (#7896)

2026-09-22 10:24:01 -07:00

cfg_pairing.py

rebase: align vllm-omni with vLLM ac9126e58aa7

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

fused_sampling.py

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

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

nucleus_ras_sampling.py

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

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

qwen3_code_predictor.py

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

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

short_kv_attention.py

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

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

snake_activation.py

[Refactor] Unify Snake/SnakeBeta and alias-free activation into common modules (#3886)

2026-05-27 23:41:35 -05:00

talker_first_audio.py

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

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

whisper_vq.py

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

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