gaoziyuan 749b2e9c89 support qwen3moe name_mapping (#2820)

2025-07-12 12:05:54 +08:00

..

ernie4_5_vl

[Executor] Move forward_meta.py to fastdeploy/model_executor (#2774)

2025-07-10 20:36:51 +08:00

__init__.py

【Fearture】support qwen2 some func (#2740)

2025-07-08 12:03:04 +08:00

deepseek_v3.py

[Executor] Move forward_meta.py to fastdeploy/model_executor (#2774)

2025-07-10 20:36:51 +08:00

ernie4_5_moe.py

[Executor] Move forward_meta.py to fastdeploy/model_executor (#2774)

2025-07-10 20:36:51 +08:00

ernie4_5_mtp.py

[Executor] Move forward_meta.py to fastdeploy/model_executor (#2774)

2025-07-10 20:36:51 +08:00

model_base.py

support qwen3moe name_mapping (#2820)

2025-07-12 12:05:54 +08:00

qwen2.py

[Executor] Move forward_meta.py to fastdeploy/model_executor (#2774)

2025-07-10 20:36:51 +08:00

qwen3.py

[Feature] support tensor-parallel-size>num_key_value_heads for qwen3 (#2799)

2025-07-11 15:09:43 +08:00

qwen3moe.py

[Feature] support tensor-parallel-size>num_key_value_heads for qwen3 (#2799)

2025-07-11 15:09:43 +08:00

tp_utils.py

Adapt for iluvatar gpu (#2684)

2025-07-07 16:53:14 +08:00

utils.py

Adapt for iluvatar gpu (#2684)

2025-07-07 16:53:14 +08:00