-
Notifications
You must be signed in to change notification settings - Fork 234
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
.github: Add basic gpu test workflow (#106)
- Loading branch information
1 parent
179a6db
commit 4ddf5fc
Showing
1 changed file
with
92 additions
and
93 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| 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 |