kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-13 22:18:36 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

fix: fnmatch usage in modeling_utils.py (#3754)

Browse Source 
Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
This commit is contained in:
Enwei Zhu 2025-04-22 13:13:53 +08:00 committed by GitHub
parent 8340657ae4
commit 353699a3b3
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
tensorrt_llm/models/modeling_utils.py
View File

@ -295,7 +295,7 @@ class LayerQuantConfig(QuantConfig):
def layer_quant_mode(self, layer_name) -> QuantMode:
for name, quant_mode in self.auto_quant_mode.items():
if fnmatch(layer_name, name):
if fnmatch.fnmatch(layer_name, name):
return quant_mode
return QuantMode(0)
@ -324,7 +324,7 @@ class LayerQuantConfig(QuantConfig):
quant_res = QuantConfig()
for name, quant_cfg in self.quantized_layers.items():
if fnmatch(module_name, name):
if fnmatch.fnmatch(module_name, name):
quant_res = quant_cfg
break
return quant_res