Sy03 d530938b5b [Model] Reuse frame-local KV in MOSS-TTS Local ...

Cache each position once while generating the audio codebooks, preserving frame-local RoPE positions and the full-prefix reference path. Share compiled batch and position shapes to avoid specialization-limit fallback. Add one compact parity regression covering frame reuse.

Signed-off-by: Sy03 <1370724210@qq.com>

2026-09-08 06:37:00 +08:00

..

model_loader

[Ming] Cleanup Ming-family shared modules (#6119)

2026-08-19 14:13:40 +08:00

models

[Model] Reuse frame-local KV in MOSS-TTS Local

2026-09-08 06:37:00 +08:00

quantization

[Quantization][Qwen3-Omni] Enable NVFP4 W4A4 serving on Blackwell (#4025)

2026-06-18 10:01:46 +08:00

stage_input_processors

[Model] Preserve MiniCPM-o Talker full attention until capacity (#6799)

2026-09-06 22:25:35 +08:00

conftest.py

[Test] Unify L2/L3 test layout, Buildkite steps, and test helpers (#2556)

2026-05-08 14:12:23 +08:00

helpers.py

[Test] Unify L2/L3 test layout, Buildkite steps, and test helpers (#2556)

2026-05-08 14:12:23 +08:00

test_cfg_pairing.py

[Model] Add MiniMax Music 3 text-to-music (#6186)

2026-08-18 04:33:13 +00:00