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
6820724e
Unverified
Commit
6820724e
authored
Jun 18, 2024
by
Tyler Michael Smith
Committed by
GitHub
Jun 19, 2024
Browse files
[Bugfix] Fix w8a8 benchmarks for int8 case (#5643)
parent
b23ce920
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
2 additions
and
3 deletions
+2
-3
benchmarks/cutlass_benchmarks/w8a8_benchmarks.py
benchmarks/cutlass_benchmarks/w8a8_benchmarks.py
+2
-3
No files found.
benchmarks/cutlass_benchmarks/w8a8_benchmarks.py
View file @
6820724e
...
@@ -120,9 +120,8 @@ def bench_int8(dtype: torch.dtype, m: int, k: int, n: int, label: str,
...
@@ -120,9 +120,8 @@ def bench_int8(dtype: torch.dtype, m: int, k: int, n: int, label: str,
# cutlass impl
# cutlass impl
timers
.
append
(
timers
.
append
(
bench_fn
(
a
,
b
,
scale_a
.
to
(
device
=
"cpu"
),
scale_b
.
to
(
device
=
"cpu"
),
bench_fn
(
a
,
b
,
scale_a
,
scale_b
,
torch
.
bfloat16
,
label
,
sub_label
,
torch
.
bfloat16
,
label
,
sub_label
,
cutlass_impl
,
cutlass_impl
,
"cutlass_i8_i8_bf16_scaled_mm"
))
"cutlass_i8_i8_bf16_scaled_mm"
))
return
timers
return
timers
...
...
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