Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
change
sglang
Commits
7eebd440
Unverified
Commit
7eebd440
authored
Jul 21, 2025
by
JieXin Liang
Committed by
GitHub
Jul 20, 2025
Browse files
[fix] fix modelopt fp4 on b200 (#8195)
parent
93d124ef
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
4 additions
and
1 deletion
+4
-1
python/sglang/srt/layers/quantization/petit.py
python/sglang/srt/layers/quantization/petit.py
+4
-1
No files found.
python/sglang/srt/layers/quantization/petit.py
View file @
7eebd440
...
...
@@ -21,6 +21,9 @@ from sglang.srt.layers.quantization.petit_utils import (
verify_petit_nvfp4_supported
,
)
from
sglang.srt.layers.quantization.utils
import
is_layer_skipped
from
sglang.srt.utils
import
is_hip
_is_hip
=
is_hip
()
# Initialize logger for the module
logger
=
logging
.
getLogger
(
__name__
)
...
...
@@ -104,7 +107,7 @@ class PetitNvFp4Config(QuantizationConfig):
@
classmethod
def
is_petit_nvfp4_compatible
(
cls
,
quant_config
:
Dict
[
str
,
Any
])
->
bool
:
quant_method
=
quant_config
.
get
(
"quant_method"
,
""
).
lower
()
return
quant_method
==
"modelopt"
return
_is_hip
and
quant_method
==
"modelopt"
def
is_layer_excluded
(
self
,
prefix
:
str
,
exclude_modules
:
list
):
for
pattern
in
exclude_modules
:
...
...
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