mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 08:21:53 +08:00
[Feature] support pooling model dummy_run (#4345)
* support qwen3-embedding * fix ci bug * support pooling dummy_run * fix * delete print * parallel_config.max_model_len * delete is_pooling_model in dummy_run * fix * fd_model * fix embedding load * fix * fix post_process
This commit is contained in:
@@ -303,7 +303,9 @@ class Qwen3ForCausalLM(ModelForCasualLM):
|
||||
if model_param_name not in params_dict:
|
||||
continue
|
||||
param = params_dict[model_param_name]
|
||||
|
||||
weight_loader = getattr(param, "weight_loader", default_weight_loader(self.fd_config))
|
||||
|
||||
weight_loader(param, loaded_weight, shard_id)
|
||||
|
||||
break
|
||||
|
||||
Reference in New Issue
Block a user