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
f78c0be8
Unverified
Commit
f78c0be8
authored
Mar 04, 2025
by
Michael Goin
Committed by
GitHub
Mar 03, 2025
Browse files
Fix benchmark_moe.py tuning for CUDA devices (#14164)
parent
66233af7
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
3 additions
and
1 deletion
+3
-1
benchmarks/kernels/benchmark_moe.py
benchmarks/kernels/benchmark_moe.py
+3
-1
No files found.
benchmarks/kernels/benchmark_moe.py
View file @
f78c0be8
...
...
@@ -2,6 +2,7 @@
import
argparse
import
time
from
contextlib
import
nullcontext
from
datetime
import
datetime
from
itertools
import
product
from
typing
import
Any
,
TypedDict
...
...
@@ -412,7 +413,8 @@ class BenchmarkWorker:
hidden_size
,
search_space
,
is_fp16
,
topk
)
with
torch
.
cuda
.
device
(
self
.
device_id
):
with
torch
.
cuda
.
device
(
self
.
device_id
)
if
current_platform
.
is_rocm
(
)
else
nullcontext
():
for
config
in
tqdm
(
search_space
):
try
:
kernel_time
=
benchmark_config
(
...
...
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