apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

fix skip_quant (#5342)
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

Browse Source 
* fix skip_quant

* fix
This commit is contained in:
Yuanle Liu
2025-12-03 13:20:51 +08:00
committed by GitHub
parent b52e1bd281
commit 17c88f429f
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
fastdeploy/model_executor/layers/linear.py
View File

@@ -508,7 +508,7 @@ class QKVParallelLinear(ColumnParallelLinear):
QKVParallelLinear Layer.
"""
def __init__(self, fd_config, prefix, with_bias=False, add_bias=True):
def __init__(self, fd_config, prefix, with_bias=False, add_bias=True, skip_quant=False):
"""
Initialize the QKV Linear layer with given parameters.
@@ -542,6 +542,7 @@ class QKVParallelLinear(ColumnParallelLinear):
output_size=output_size,
with_bias=with_bias,
add_bias=add_bias,
skip_quant=skip_quant,
)
def _get_shard_size_mapping(self, loaded_shard_id: str):
@@ -720,7 +721,6 @@ class RowParallelLinear(LinearBase):
skip_quant (bool): Whether to skip quantization. Defaults to False.
"""
self.fd_config = fd_config
self.skip_quant = False
self.nranks = fd_config.parallel_config.tensor_parallel_size
self.tp_group = fd_config.parallel_config.tp_group
self.hidden_size = fd_config.model_config.hidden_size