Kane2011 2ae7ab28d2 [MetaxGPU] adapt to the latest fastdeploy on metax gpu (#3492)

2025-08-25 17:44:20 +08:00

..

graph_optimization

[Excutor] Change cudagraph hashkey from batch size to num_tokens (#3454)

2025-08-18 16:16:48 +08:00

guided_decoding

add error traceback info (#3419)

2025-08-19 19:32:04 +08:00

layers

[MetaxGPU] adapt to the latest fastdeploy on metax gpu (#3492)

2025-08-25 17:44:20 +08:00

model_loader

[V1 Loader] support weight_only (#3413)

2025-08-23 13:13:41 +08:00

models

support w4afp8 EP inference (#3044)

2025-08-25 11:27:45 +08:00

ops

…

__init__.py

…

forward_meta.py

[Excutor] Increase buffer size to prevent address corruption; add forward metadata debug tool (#3404)

2025-08-18 16:14:09 +08:00

load_weight_utils.py

…

pre_and_post_process.py

[MetaxGPU] adapt to the latest fastdeploy on metax gpu (#3492)

2025-08-25 17:44:20 +08:00

utils.py

[V1 Loader] support weight_only (#3413)

2025-08-23 13:13:41 +08:00