Skip to content
This repository was archived by the owner on Sep 10, 2025. It is now read-only.

Commit 0c33e0b

Browse files
committed
fix ci test
1 parent f8124e6 commit 0c33e0b

File tree

1 file changed

+4
-4
lines changed

1 file changed

+4
-4
lines changed

.github/workflows/pull.yml

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1096,14 +1096,14 @@ jobs:
10961096
wget -O ./tokenizer.model https://github.com/karpathy/llama2.c/raw/master/tokenizer.model
10971097
export PRMT="Once upon a time in a land far away"
10981098
echo "Generate eager"
1099-
python torchchat.py generate stories110M --temperature 0 --prompt "${PRMT}" --device cpu --quantize '{"linear:a8wxdq": {"bitwidth": 4, "groupsize": 256, "has_weight_zeros": false}}'
1099+
python torchchat.py generate stories110M --temperature 0 --prompt "${PRMT}" --device cpu --dtype float32 --quantize '{"linear:a8wxdq": {"bitwidth": 4, "groupsize": 256, "has_weight_zeros": false}}'
11001100
echo "Generate compile"
1101-
python torchchat.py generate stories110M --temperature 0 --prompt "${PRMT}" --device cpu --quantize '{"linear:a8wxdq": {"bitwidth": 4, "groupsize": 256, "has_weight_zeros": false}}' --compile
1101+
python torchchat.py generate stories110M --temperature 0 --prompt "${PRMT}" --device cpu --dtype float32 --quantize '{"linear:a8wxdq": {"bitwidth": 4, "groupsize": 256, "has_weight_zeros": false}}' --compile
11021102
echo "Export and run ET (C++ runner)"
1103-
python torchchat.py export stories110M --output-pte-path ./model.pte --quantize '{"linear:a8wxdq": {"bitwidth": 4, "groupsize": 256, "has_weight_zeros": false}}'
1103+
python torchchat.py export stories110M --output-pte-path ./model.pte --dtype float32 --quantize '{"linear:a8wxdq": {"bitwidth": 4, "groupsize": 256, "has_weight_zeros": false}}'
11041104
./cmake-out/et_run ./model.pte -z ./tokenizer.model -t 0 -i "${PRMT}"
11051105
echo "Export and run AOTI (C++ runner)"
1106-
python torchchat.py export stories110M --output-dso-path ./model.so --quantize '{"linear:a8wxdq": {"bitwidth": 4, "groupsize": 256, "has_weight_zeros": false}}'
1106+
python torchchat.py export stories110M --output-dso-path ./model.so --dtype float32 --quantize '{"linear:a8wxdq": {"bitwidth": 4, "groupsize": 256, "has_weight_zeros": false}}'
11071107
./cmake-out/aoti_run ./model.so -z ./tokenizer.model -t 0 -i "${PRMT}"
11081108
echo "Generate AOTI"
11091109
python torchchat.py generate stories110M --dso-path ./model.so --prompt "${PRMT}"

0 commit comments

Comments
 (0)