biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Misc] Move print_*_once from utils to logger (#11298)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Maxime Fournioux <55544262+mfournioux@users.noreply.github.com>
Co-authored-by: Maxime Fournioux <55544262+mfournioux@users.noreply.github.com>
This commit is contained in:
Cyrus Leung
2025-01-09 12:48:12 +08:00
committed by GitHub
parent 730e9592e9
commit d848800e88
21 changed files with 129 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/model_executor/layers/quantization/fp8.py
View File

@@ -28,7 +28,6 @@ from vllm.model_executor.parameter import (BlockQuantScaleParameter,
PerTensorScaleParameter)
from vllm.model_executor.utils import set_weight_attrs
from vllm.platforms import current_platform
from vllm.utils import print_warning_once
ACTIVATION_SCHEMES = ["static", "dynamic"]
@@ -539,10 +538,10 @@ class Fp8MoEMethod(FusedMoEMethodBase):
"activation scales are None.")
if (not all_close_1d(layer.w13_input_scale)
or not all_close_1d(layer.w2_input_scale)):
print_warning_once(
logger.warning_once(
"Found input_scales that are not equal for "
"fp8 MoE layer. Using the maximum across experts "
"for each layer. ")
"for each layer.")
layer.w13_input_scale = torch.nn.Parameter(
layer.w13_input_scale.max(), requires_grad=False)
layer.w2_input_scale = torch.nn.Parameter(