Viacheslav KlimkovandYueqian Lin 914e92cf80 [Refactor][Qwen3-TTS] Extract reusable prompt-embeds builder and make tts_pad_embed a persistent buffer (#3992) ...

Signed-off-by: Viacheslav Klimkov <vklimkov@nvidia.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>

2026-05-30 16:11:00 +08:00

..

__init__.py

feat(qwen3-tts): Add CUDA Graph support for speech tokenizer decoder (#1205)

2026-02-27 10:48:25 +08:00

test_code_predictor_dtype.py

[TTS][Perf] Optimize Qwen3-TTS high-concurrency serving (#3662)

2026-05-17 16:58:59 -04:00

test_cuda_graph_decoder.py

[Bugfix] Fix Triton SnakeBeta kernel for bf16/fp16 inputs (#3472)

2026-05-28 17:10:36 +00:00

test_qwen3_tts_code2wav.py

[TTS][Perf] Optimize Qwen3-TTS high-concurrency serving (#3662)

2026-05-17 16:58:59 -04:00

test_qwen3_tts_talker_preprocess.py

[Refactor][Qwen3-TTS] Extract reusable prompt-embeds builder and make tts_pad_embed a persistent buffer (#3992)

2026-05-30 16:11:00 +08:00

test_qwen3_tts_talker_prompt_len.py

[Refactor][Qwen3-TTS] Extract reusable prompt-embeds builder and make tts_pad_embed a persistent buffer (#3992)

2026-05-30 16:11:00 +08:00