3 people 57227dc7f3 [Perf][Bugfix] qwen3-tts hot path: prefix-cache OOM guards + talker/orchestrator micro-opts (#3689) ...

Signed-off-by: JuanPZuluaga <juanz9312@gmal.com>
Co-authored-by: JuanPZuluaga <juanz9312@gmal.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>

2026-06-09 10:36:57 -07:00

..

layers

[Cleanup] Extract shared SinusPositionEmbedding/DiTTimestepEmbedding/timestep_embedding layer (#3285)

2026-05-01 20:19:42 +08:00

model_loader

[Fix]Ensure HuggingFace downloads complete before initialization. (#1213)

2026-02-10 16:05:12 +08:00

models

[Perf][Bugfix] qwen3-tts hot path: prefix-cache OOM guards + talker/orchestrator micro-opts (#3689)

2026-06-09 10:36:57 -07:00

stage_configs

[Quant] ModelOpt FP8 for Wan2.2 & HunyuanVideo-1.5 video-gen (#3305)

2026-06-08 02:53:06 +08:00

stage_input_processors

[Fix][HiggsAudioV3] Fix ramp-down off-by-one crash and buffer state bugs in Stage0 talker (#4219)

2026-06-08 17:33:20 +00:00

__init__.py

update ar_dit_test

2025-09-28 21:58:48 +08:00

custom_process_mixin.py

[Core] customize process between stages, remove the need of "request_ids" in model forward, rebase to 0.12.0 (#458)

2025-12-24 13:26:33 +00:00