Gao Han 5cf2681aeb Revert "[Perf][Qwen3-TTS] Fuse QKV and gate_up projections in code predictor …" ...

This reverts commit 6fdc4ca62d.

2026-08-04 22:25:12 +08:00

..

layers

Add NPU support for OmniMRotaryEmbedding (#3609)

2026-06-18 16:58:40 +08:00

model_loader

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

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

models

Revert "[Perf][Qwen3-TTS] Fuse QKV and gate_up projections in code predictor …"

2026-08-04 22:25:12 +08:00

stage_input_processors

[Bugfix] Qwen3-TTS full-payload: emit one placeholder frame on a degenerate take instead of an empty payload (#5472)

2026-07-30 14:27:39 +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