Lukas Geiger 5a87076d6e

[Model][QwenVL] Optimize Qwen2_5_VisionAttention q,k preparation (#28769) ...

Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

2025-11-16 17:37:15 +00:00

..

layers

[Kernel][Moe Configs] llama4 maverick fp8 moe config tp8 on mi325 (#28709)

2025-11-15 01:10:48 -08:00

model_loader

Skip models that cannot currently init on Transformers v5 (#28471)

2025-11-12 23:43:57 +00:00

models

[Model][QwenVL] Optimize Qwen2_5_VisionAttention q,k preparation (#28769)

2025-11-16 17:37:15 +00:00

warmup

[Core] Encoder separation for Encode-Prefill-Decode Disaggregation (#25233)

2025-11-11 18:58:33 -08:00

__init__.py

…

custom_op.py

…

parameter.py

…

utils.py

…