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

Revert "Enable FP64 emulation for E2E AlbertForMaskedLM test on A770 (#1879)" #2314

Merged
merged 1 commit into from
Sep 23, 2024
Merged

Revert "Enable FP64 emulation for E2E AlbertForMaskedLM test on A770 (#1879)" #2314

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
9 changes: 0 additions & 9 deletions .github/workflows/build-test-reusable.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -169,15 +169,6 @@ jobs:
export WORKSPACE=$GITHUB_WORKSPACE
cd pytorch
pip install pyyaml pandas scipy numpy psutil pyre_extensions torchrec

source $GITHUB_WORKSPACE/scripts/capture-hw-details.sh
if [[ $GPU_DEVICE = *A770* ]]; then
# To enable FP64 type emulation.
# For details see: https://github.com/intel/intel-xpu-backend-for-triton/pull/1879
export OverrideDefaultFP64Settings=1
export IGC_EnableDPEmulation=1
fi

# TODO: Find the fastest Hugging Face model
$GITHUB_WORKSPACE/scripts/inductor_xpu_test.sh huggingface float32 inference accuracy xpu 0 static 1 0 AlbertForMaskedLM
# The script above always returns 0, so we need an additional check to see if the accuracy test passed
Expand Down