Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
OpenDAS
vllm_cscc
Commits
c5e83309
Unverified
Commit
c5e83309
authored
Jul 22, 2024
by
Cheng Li
Committed by
GitHub
Jul 22, 2024
Browse files
[Bugfix] Fix null `modules_to_not_convert` in FBGEMM Fp8 quantization (#6665)
parent
e0c15758
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
1 addition
and
1 deletion
+1
-1
vllm/model_executor/layers/quantization/fbgemm_fp8.py
vllm/model_executor/layers/quantization/fbgemm_fp8.py
+1
-1
No files found.
vllm/model_executor/layers/quantization/fbgemm_fp8.py
View file @
c5e83309
...
...
@@ -31,7 +31,7 @@ class FBGEMMFp8Config(QuantizationConfig):
"""Config class for FBGEMM Fp8."""
def
__init__
(
self
,
ignore_list
:
List
[
str
],
input_scale_ub
:
float
):
self
.
ignore_list
=
ignore_list
self
.
ignore_list
=
ignore_list
if
ignore_list
else
[]
self
.
input_scale_ub
=
input_scale_ub
# For GPUs that lack FP8 hardware support, we can leverage the Marlin
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment