lifulll 72094d4d82 enable dcu ci (#3402)

2025-08-29 10:23:08 +08:00

..

__init__.py

…

dcu_model_runner.py

enable dcu ci (#3402)

2025-08-29 10:23:08 +08:00

dcu_worker.py

enable dcu ci (#3402)

2025-08-29 10:23:08 +08:00

eplb.py

…

experts_manager.py

…

gcu_model_runner.py

[NewFeature]Support dp multi api server && Fix some bug in mixed ep && merge develop (#3598)

2025-08-26 19:59:02 +08:00

gcu_worker.py

…

gpu_model_runner.py

enable dcu ci (#3402)

2025-08-29 10:23:08 +08:00

gpu_worker.py

Modified to support custom all reduce by default (#3538)

2025-08-22 16:59:05 +08:00

iluvatar_model_runner.py

…

iluvatar_worker.py

…

metax_model_runner.py

[V1 Loader]support param create and load for wint2 and xpu backend (#3581)

2025-08-28 09:49:36 +08:00

metax_worker.py

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

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

model_runner_base.py

…

output.py

…

utils.py

add error traceback info (#3419)

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

worker_base.py

…

worker_process.py

add input_processor plugin (#3657)

2025-08-28 22:53:57 +08:00

xpu_model_runner.py

[fix] qwen output inconsistency when top_p=0 (#3634)

2025-08-27 17:16:23 +08:00

xpu_worker.py

revert pr (#3481)

2025-08-21 14:19:50 +08:00