squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Bugfix]fix and needs_scalar_to_array logic check (#6238)

Browse Source 
Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com>
This commit is contained in:
Baoyuan Qi 2024-07-10 07:43:24 +08:00 committed by GitHub
parent 673dd4cae9
commit d3a245138a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -387,7 +387,7 @@ class MergedColumnParallelLinear(ColumnParallelLinear):
if loaded_shard_id is None:
# Loaded weight is already fused on disk (qkv/mlp).
if output_dim is None:
if needs_scalar_to_array is not None:
if needs_scalar_to_array:
param_data, loaded_weight = adjust_scalar_to_fused_array(
param_data, loaded_weight, 0)
@ -549,7 +549,7 @@ class QKVParallelLinear(ColumnParallelLinear):
if loaded_shard_id is None:
# Loaded weight is already fused on disk (qkv/mlp).
if output_dim is None:
if needs_scalar_to_array is not None:
if needs_scalar_to_array:
param_data, loaded_weight = adjust_scalar_to_fused_array(
param_data, loaded_weight, 0)