3 people 6fdc4ca62d [Perf][Qwen3-TTS] Fuse QKV and gate_up projections in code predictor (#4958) ...

Signed-off-by: sheenlin <sheenlin@tencent.com>
Co-authored-by: sheenlin <sheenlin@tencent.com>
Co-authored-by: yurain <yurain26@users.noreply.github.com>

2026-08-04 11:59:32 +00:00

..

ming

[Perf] Ming-TTS Stage-0 flow-head speedup: RoPE/QKV fusion, opt-in torch.compile, PIECEWISE cudagraph (#4942)

2026-07-12 19:50:51 -07:00

__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

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

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

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

[Perf][Qwen3-TTS] Fuse QKV and gate_up projections in code predictor (#4958)

2026-08-04 11:59:32 +00:00

snake_activation.py

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

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

whisper_vq.py

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

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