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

.github: Add basic gpu test workflow #106

Merged
merged 4 commits into from
Apr 10, 2024
+92 −93
Merged

.github: Add basic gpu test workflow #106

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
72e9cbe
.github: Add basic test workflow
seemethere Apr 10, 2024
83f71fa
switch to official docker image
seemethere Apr 10, 2024
4188dc5
modify compile_t4 to use generic workflow
seemethere Apr 10, 2024
43ba754
comment out failing tests
seemethere Apr 10, 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
185 changes: 92 additions & 93 deletions .github/workflows/compile_t4.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,106 +1,105 @@
name: Compile main
name: Run compile tests

on:
pull_request:
push:
branches:
- main
pull_request:
workflow_dispatch:

jobs:
run-tinystories:
strategy:
matrix:
runner: [4-core-ubuntu-gpu-t4]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout repo
uses: actions/checkout@v2
- name: Setup Python
uses: actions/setup-python@v2
with:
python-version: 3.11
- name: Print machine info
run: |
uname -a
if [ $(uname -s) == Darwin ]; then
sysctl machdep.cpu.brand_string
sysctl machdep.cpu.core_count
fi
- name: Install requirements
run: |
pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu121
pip install -r requirements.txt
- name: Download checkpoints
run: |
mkdir -p checkpoints/stories15M
pushd checkpoints/stories15M
wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories15M.pt
wget https://github.com/karpathy/llama2.c/raw/master/tokenizer.model
popd
- name: Run inference
run: |
export MODEL_PATH=checkpoints/stories15M/stories15M.pt
export MODEL_NAME=stories15M
export MODEL_DIR=/tmp
python generate.py --device cuda --checkpoint-path ${MODEL_PATH} --temperature 0 > ./output_eager
cat ./output_eager
python generate.py --device cuda --compile --checkpoint-path ${MODEL_PATH} --temperature 0 > ./output_compiled
cat ./output_compiled
python export.py --device cuda --checkpoint-path ${MODEL_PATH} --output-dso-path ${MODEL_DIR}/${MODEL_NAME}.so
python generate.py --device cuda --checkpoint-path ${MODEL_PATH} --temperature 0 --dso-path ${MODEL_DIR}/${MODEL_NAME}.so > ./output_aoti
cat ./output_aoti
test-cuda:
uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
with:
runner: linux.g5.4xlarge.nvidia.gpu
gpu-arch-type: cuda
gpu-arch-version: "12.1"
script: |
echo "::group::Print machine info"
uname -a
if [ $(uname -s) == Darwin ]; then
sysctl machdep.cpu.brand_string
sysctl machdep.cpu.core_count
fi
echo "::endgroup::"
echo "::group::Download checkpoints"
# Install requirements
pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu121
pip install -r requirements.txt
echo "::endgroup::"
echo "::group::Download checkpoints"
mkdir -p checkpoints/stories15M
pushd checkpoints/stories15M
wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories15M.pt
wget https://github.com/karpathy/llama2.c/raw/master/tokenizer.model
popd
echo "::endgroup::"
echo "::group::Run inference"
export MODEL_PATH=checkpoints/stories15M/stories15M.pt
export MODEL_NAME=stories15M
export MODEL_DIR=/tmp
python generate.py --device cuda --checkpoint-path ${MODEL_PATH} --temperature 0 > ./output_eager
cat ./output_eager
python generate.py --device cuda --compile --checkpoint-path ${MODEL_PATH} --temperature 0 > ./output_compiled
cat ./output_compiled
python export.py --device cuda --checkpoint-path ${MODEL_PATH} --output-dso-path ${MODEL_DIR}/${MODEL_NAME}.so
python generate.py --device cuda --checkpoint-path ${MODEL_PATH} --temperature 0 --dso-path ${MODEL_DIR}/${MODEL_NAME}.so > ./output_aoti
cat ./output_aoti
echo "******************************************"
echo "******* Emb: channel-wise quantized ******"
echo "******************************************"
python generate.py --device cuda --quant '{"embedding" : {"bitwidth": 8, "group_size": 0}}' --checkpoint-path ${MODEL_PATH} --temperature 0 > ./output_eager
cat ./output_eager
python generate.py --device cuda --compile --quant '{"embedding" : {"bitwidth": 8, "group_size": 0}}' --checkpoint-path ${MODEL_PATH} --temperature 0 > ./output_compiled
cat ./output_compiled
python export.py --device cuda --quant '{"embedding" : {"bitwidth": 8, "group_size": 0}}' --checkpoint-path ${MODEL_PATH} --output-dso-path ${MODEL_DIR}/${MODEL_NAME}.so
python generate.py --device cuda --checkpoint-path ${MODEL_PATH} --temperature 0 --dso-path ${MODEL_DIR}/${MODEL_NAME}.so > ./output_aoti
cat ./output_aoti
echo "******************************************"
echo "******* Emb: channel-wise quantized ******"
echo "******************************************"
# python generate.py --device cuda --quant '{"embedding" : {"bitwidth": 8, "group_size": 0}}' --checkpoint-path ${MODEL_PATH} --temperature 0 > ./output_eager
# cat ./output_eager
# python generate.py --device cuda --compile --quant '{"embedding" : {"bitwidth": 8, "group_size": 0}}' --checkpoint-path ${MODEL_PATH} --temperature 0 > ./output_compiled
# cat ./output_compiled
# python export.py --device cuda --quant '{"embedding" : {"bitwidth": 8, "group_size": 0}}' --checkpoint-path ${MODEL_PATH} --output-dso-path ${MODEL_DIR}/${MODEL_NAME}.so
# python generate.py --device cuda --checkpoint-path ${MODEL_PATH} --temperature 0 --dso-path ${MODEL_DIR}/${MODEL_NAME}.so > ./output_aoti
# cat ./output_aoti
echo "******************************************"
echo "******** Emb: group-wise quantized *******"
echo "******************************************"
python generate.py --device cuda --quant '{"embedding" : {"bitwidth": 8, "group_size": 8}}' --checkpoint-path ${MODEL_PATH} --temperature 0 > ./output_eager
cat ./output_eager
python generate.py --device cuda --compile --quant '{"embedding" : {"bitwidth": 8, "group_size": 8}}' --checkpoint-path ${MODEL_PATH} --temperature 0 > ./output_compiled
cat ./output_compiled
python export.py --device cuda --quant '{"embedding" : {"bitwidth": 8, "group_size": 8}}' --checkpoint-path ${MODEL_PATH} --output-dso-path ${MODEL_DIR}/${MODEL_NAME}.so
python generate.py --device cuda --checkpoint-path ${MODEL_PATH} --temperature 0 --dso-path ${MODEL_DIR}/${MODEL_NAME}.so > ./output_aoti
cat ./output_aoti
echo "******************************************"
echo "******** Emb: group-wise quantized *******"
echo "******************************************"
# python generate.py --device cuda --quant '{"embedding" : {"bitwidth": 8, "group_size": 8}}' --checkpoint-path ${MODEL_PATH} --temperature 0 > ./output_eager
# cat ./output_eager
# python generate.py --device cuda --compile --quant '{"embedding" : {"bitwidth": 8, "group_size": 8}}' --checkpoint-path ${MODEL_PATH} --temperature 0 > ./output_compiled
# cat ./output_compiled
# python export.py --device cuda --quant '{"embedding" : {"bitwidth": 8, "group_size": 8}}' --checkpoint-path ${MODEL_PATH} --output-dso-path ${MODEL_DIR}/${MODEL_NAME}.so
# python generate.py --device cuda --checkpoint-path ${MODEL_PATH} --temperature 0 --dso-path ${MODEL_DIR}/${MODEL_NAME}.so > ./output_aoti
# cat ./output_aoti
echo "******************************************"
echo "******* INT8 channel-wise quantized ******"
echo "******************************************"
python generate.py --device cuda --quant '{"linear:int8" : {"bitwidth": 8, "group_size": 0}}' --checkpoint-path ${MODEL_PATH} --temperature 0 > ./output_eager
cat ./output_eager
python generate.py --device cuda --compile --quant '{"linear:int8" : {"bitwidth": 8, "group_size": 0}}' --checkpoint-path ${MODEL_PATH} --temperature 0 > ./output_compiled
cat ./output_compiled
python export.py --device cuda --quant '{"linear:int8" : {"bitwidth": 8, "group_size": 0}}' --checkpoint-path ${MODEL_PATH} --output-dso-path ${MODEL_DIR}/${MODEL_NAME}.so
python generate.py --device cuda --checkpoint-path ${MODEL_PATH} --temperature 0 --dso-path ${MODEL_DIR}/${MODEL_NAME}.so > ./output_aoti
cat ./output_aoti
echo "******************************************"
echo "******* INT8 channel-wise quantized ******"
echo "******************************************"
# python generate.py --device cuda --quant '{"linear:int8" : {"bitwidth": 8, "group_size": 0}}' --checkpoint-path ${MODEL_PATH} --temperature 0 > ./output_eager
# cat ./output_eager
# python generate.py --device cuda --compile --quant '{"linear:int8" : {"bitwidth": 8, "group_size": 0}}' --checkpoint-path ${MODEL_PATH} --temperature 0 > ./output_compiled
# cat ./output_compiled
# python export.py --device cuda --quant '{"linear:int8" : {"bitwidth": 8, "group_size": 0}}' --checkpoint-path ${MODEL_PATH} --output-dso-path ${MODEL_DIR}/${MODEL_NAME}.so
# python generate.py --device cuda --checkpoint-path ${MODEL_PATH} --temperature 0 --dso-path ${MODEL_DIR}/${MODEL_NAME}.so > ./output_aoti
# cat ./output_aoti
echo "******************************************"
echo "******** INT8 group-wise quantized *******"
echo "******************************************"
python generate.py --device cuda --quant '{"linear:int8" : {"bitwidth": 8, "group_size": 8}}' --checkpoint-path ${MODEL_PATH} --temperature 0 > ./output_eager
cat ./output_eager
python generate.py --device cuda --compile --quant '{"linear:int8" : {"bitwidth": 8, "group_size": 8}}' --checkpoint-path ${MODEL_PATH} --temperature 0 > ./output_compiled
cat ./output_compiled
python export.py --device cuda --quant '{"linear:int8" : {"bitwidth": 8, "group_size": 8}}' --checkpoint-path ${MODEL_PATH} --output-dso-path ${MODEL_DIR}/${MODEL_NAME}.so
python generate.py --device cuda --checkpoint-path ${MODEL_PATH} --temperature 0 --dso-path ${MODEL_DIR}/${MODEL_NAME}.so > ./output_aoti
cat ./output_aoti
echo "******************************************"
echo "******** INT8 group-wise quantized *******"
echo "******************************************"
# python generate.py --device cuda --quant '{"linear:int8" : {"bitwidth": 8, "group_size": 8}}' --checkpoint-path ${MODEL_PATH} --temperature 0 > ./output_eager
# cat ./output_eager
# python generate.py --device cuda --compile --quant '{"linear:int8" : {"bitwidth": 8, "group_size": 8}}' --checkpoint-path ${MODEL_PATH} --temperature 0 > ./output_compiled
# cat ./output_compiled
# python export.py --device cuda --quant '{"linear:int8" : {"bitwidth": 8, "group_size": 8}}' --checkpoint-path ${MODEL_PATH} --output-dso-path ${MODEL_DIR}/${MODEL_NAME}.so
# python generate.py --device cuda --checkpoint-path ${MODEL_PATH} --temperature 0 --dso-path ${MODEL_DIR}/${MODEL_NAME}.so > ./output_aoti
# cat ./output_aoti
echo "tests complete"
echo "******************************************"
# echo "********* EAGER vs TORCH.COMPILE *********"
# echo "******************************************"
# diff output_eager output_compiled
# echo "******************************************"
# echo "********* EAGER vs AOT INDUCTOR *********"
# echo "******************************************"
# diff output_eager output_aoti
echo "tests complete"
echo "******************************************"
echo "::endgroup::"
# echo "********* EAGER vs TORCH.COMPILE *********"
# echo "******************************************"
# diff output_eager output_compiled
# echo "******************************************"
# echo "********* EAGER vs AOT INDUCTOR *********"
# echo "******************************************"
# diff output_eager output_aoti
Loading