apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

support qwen2 weight only (#3571)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Details
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
Details
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
Details
CE Compile Job / Show Code Archive Output (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
Details
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Details
Deploy GitHub Pages / deploy (push) Has been cancelled
Details
Publish Job / publish_pre_check (push) Has been cancelled
Details
Publish Job / print_publish_pre_check_outputs (push) Has been cancelled
Details
Publish Job / FD-Clone-Linux (push) Has been cancelled
Details
Publish Job / Show Code Archive Output (push) Has been cancelled
Details
Publish Job / BUILD_SM8090 (push) Has been cancelled
Details
Publish Job / BUILD_SM8689 (push) Has been cancelled
Details
Publish Job / PADDLE_PYPI_UPLOAD_8090 (push) Has been cancelled
Details
Publish Job / PADDLE_PYPI_UPLOAD_8689 (push) Has been cancelled
Details
Publish Job / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
Details
Publish Job / Run FastDeploy LogProb Tests (push) Has been cancelled
Details
Publish Job / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
Details
Publish Job / Run Base Tests (push) Has been cancelled
Details
Publish Job / Run Accuracy Tests (push) Has been cancelled
Details

Browse Source
This commit is contained in:
bukejiyu
2025-08-24 11:14:34 +08:00
committed by GitHub
parent 77514e3e1e
commit bdbac0aa3d
3 changed files with 25 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
fastdeploy/model_executor/models/qwen2.py
View File

@@ -16,6 +16,7 @@
from __future__ import annotations
import re
from functools import partial
import paddle
@@ -314,7 +315,10 @@ class Qwen2ForCausalLM(ModelForCasualLM):
weights_iterator (Iterator): An iterator yielding (name, weight) pairs.
"""
from fastdeploy.model_executor.models.utils import default_weight_loader
from fastdeploy.model_executor.utils import (
default_weight_loader,
process_weights_after_loading,
)
stacked_params_mapping = [
# (param_name, shard_name, shard_id)
@@ -328,6 +332,7 @@ class Qwen2ForCausalLM(ModelForCasualLM):
]
params_dict = dict(self.named_parameters())
process_weights_after_loading_fn = process_weights_after_loading(dict(self.named_sublayers()))
for loaded_weight_name, loaded_weight in weights_iterator:
for param_name, weight_name, shard_id in stacked_params_mapping:
if weight_name not in loaded_weight_name:
@@ -340,11 +345,14 @@ class Qwen2ForCausalLM(ModelForCasualLM):
weight_loader(param, loaded_weight, shard_id)
break
else:
if loaded_weight_name not in params_dict:
model_param_name = loaded_weight_name
if model_param_name not in params_dict:
continue
param = params_dict[loaded_weight_name]
param = params_dict[model_param_name]
weight_loader = getattr(param, "weight_loader", default_weight_loader(self.fd_config))
weight_loader(param, loaded_weight)
model_sublayer_name = re.sub(r"\.(weight)$", "", model_param_name)
process_weights_after_loading_fn(model_sublayer_name, param)
@classmethod
def name(self):