Skip to content

update torchao pin: optimized mps lowbit shaders #1428

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.

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

Merged
merged 2 commits into from
Dec 18, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
2 changes: 1 addition & 1 deletion install/.pins/torchao-pin.txt
Original file line number Diff line number Diff line change
@@ -1 +1 @@
7d7c14e898eca3fe66138d2a9445755a9270b800
2e032c6b0de960dee554dcb08126ace718b14c6d
2 changes: 2 additions & 0 deletions torchchat/utils/quantize.py
Original file line number Diff line number Diff line change
Expand Up @@ -932,13 +932,15 @@ def quantized_model(self) -> nn.Module:
libs = glob.glob(f"{torchao_build_path}/cmake-out/lib/libtorchao_ops_aten.*")
libs = list(filter(lambda l: (l.endswith("so") or l.endswith("dylib")), libs))
torch.ops.load_library(libs[0])
print("Loaded torchao cpu ops.")
except Exception as e:
print("Unabled to load torchao cpu ops library. Slow fallback kernels will be used.")

try:
libname = "libtorchao_ops_mps_aten.dylib"
libpath = f"{torchao_build_path}/cmake-out/lib/{libname}"
torch.ops.load_library(libpath)
print("Loaded torchao mps ops.")
except Exception as e:
print("Unabled to load torchao mps ops library.")

Expand Down
Loading