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
4b4512fa
"tests/entrypoints/pooling/basic/test_encode.py" did not exist on "2c5e637b57bcb2d5b3c7d992fd8b75a8bbeafcc3"
Commit
4b4512fa
authored
Dec 02, 2025
by
zhuwenwen
Browse files
add gfx938
parent
d4d251fe
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
2 additions
and
2 deletions
+2
-2
CMakeLists.txt
CMakeLists.txt
+1
-1
vllm/utils/__init__.py
vllm/utils/__init__.py
+1
-1
No files found.
CMakeLists.txt
View file @
4b4512fa
...
...
@@ -38,7 +38,7 @@ install(CODE "set(CMAKE_INSTALL_LOCAL_ONLY TRUE)" ALL_COMPONENTS)
set
(
PYTHON_SUPPORTED_VERSIONS
"3.9"
"3.10"
"3.11"
"3.12"
)
# Supported AMD GPU architectures.
set
(
HIP_SUPPORTED_ARCHS
"gfx908;gfx90a;gfx942;gfx950;gfx1030;gfx1100;gfx1101;gfx1200;gfx1201;gfx906;gfx926;gfx928;gfx936"
)
set
(
HIP_SUPPORTED_ARCHS
"gfx908;gfx90a;gfx942;gfx950;gfx1030;gfx1100;gfx1101;gfx1200;gfx1201;gfx906;gfx926;gfx928;gfx936
;gfx938
"
)
#
# Supported/expected torch versions for CUDA/ROCm.
...
...
vllm/utils/__init__.py
View file @
4b4512fa
...
...
@@ -86,7 +86,7 @@ POOLING_MODEL_MAX_NUM_BATCHED_TOKENS = 32768
MULTIMODAL_MODEL_MAX_NUM_BATCHED_TOKENS
=
5120
GPU_ARCH
=
torch
.
cuda
.
get_device_properties
(
"cuda"
).
gcnArchName
SUPPORT_TC
=
any
(
arch
in
GPU_ARCH
for
arch
in
[
"gfx928"
,
"gfx936"
])
SUPPORT_TC
=
any
(
arch
in
GPU_ARCH
for
arch
in
[
"gfx928"
,
"gfx936"
"gfx938"
])
def
_generate_random_int8
(
tensor
:
torch
.
Tensor
,
...
...
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