Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix CI after do_bench refactor in pytorch inductor #242

Merged
merged 2 commits into from
May 14, 2024
Merged

Fix CI after do_bench refactor in pytorch inductor #242

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2c95b52
Fix CI after do_bench refactor in pytorch inductor
jerryzh168 May 14, 2024
adb4b06
Merge branch 'main' into fix-ci
jerryzh168 May 14, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 7 additions & 1 deletion torchao/quantization/autoquant.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,8 @@
except:
from torch._inductor.runtime.runtime_utils import do_bench

from .utils import TORCH_VERSION_AFTER_2_4

aten = torch.ops.aten

AUTOQUANT_CACHE = {}
Expand Down Expand Up @@ -197,7 +199,11 @@ def do_autoquant_bench(op, *args, **kwargs):
graph = torch.cuda.CUDAGraph()
with torch.cuda.graph(graph, stream=stream):
op(*args, **kwargs)
res = do_bench(lambda: graph.replay(), warmup=warmup, rep=rep, return_mode="median")
if TORCH_VERSION_AFTER_2_4:
from torch._inductor.runtime.runtime_utils import do_bench_gpu
res = do_bench_gpu(lambda: graph.replay(), warmup=warmup, rep=rep, return_mode="median")
else:
res = do_bench(lambda: graph.replay(), warmup=warmup, rep=rep, return_mode="median")
return res

def _is_interpolate_mode(mode):
Expand Down
Loading