enable llava on torchchat #1903
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
| name: Run the aoti runner with CUDA using stories | |
| on: | |
| pull_request: | |
| push: | |
| branches: | |
| - main | |
| workflow_dispatch: | |
| jobs: | |
| test-runner-aot-cuda: | |
| uses: pytorch/test-infra/.github/workflows/linux_job.yml@main | |
| with: | |
| runner: linux.g5.4xlarge.nvidia.gpu | |
| secrets-env: "HF_TOKEN_PERIODIC" | |
| gpu-arch-type: cuda | |
| gpu-arch-version: "12.1" | |
| timeout: 60 | |
| script: | | |
| echo "::group::Print machine info" | |
| uname -a | |
| echo "::endgroup::" | |
| echo "::group::Install newer objcopy that supports --set-section-alignment" | |
| yum install -y devtoolset-10-binutils | |
| export PATH=/opt/rh/devtoolset-10/root/usr/bin/:$PATH | |
| echo "::endgroup::" | |
| echo "::group::Download checkpoints" | |
| # Install requirements | |
| ./install/install_requirements.sh cuda | |
| bash torchchat/utils/scripts/build_native.sh aoti | |
| pip3 list | |
| python3 -c 'import torch;print(f"torch: {torch.__version__, torch.version.git_version}")' | |
| echo "::endgroup::" | |
| echo "::group::Download checkpoints" | |
| mkdir -p checkpoints/stories15M | |
| pushd checkpoints/stories15M | |
| wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories15M.pt | |
| wget https://github.com/karpathy/llama2.c/raw/master/tokenizer.model | |
| popd | |
| echo "::endgroup::" | |
| echo "::group::Run inference" | |
| export MODEL_PATH=checkpoints/stories15M/stories15M.pt | |
| export MODEL_NAME=stories15M | |
| export MODEL_DIR=/tmp | |
| set -eou pipefail | |
| export MODEL_DIR=${PWD}/checkpoints/stories15M | |
| export PROMPT="Once upon a time in a land far away" | |
| for DTYPE in bfloat16; do | |
| python torchchat.py generate --dtype ${DTYPE} --checkpoint-path ${MODEL_DIR}/stories15M.pt --temperature 0 --prompt "${PROMPT}" --device cuda | |
| python torchchat.py export --checkpoint-path ${MODEL_DIR}/stories15M.pt --output-dso-path /tmp/model.so | |
| ./cmake-out/aoti_run /tmp/model.so -d CUDA -z ${MODEL_DIR}/tokenizer.model -i "${PROMPT}" | |
| done | |
| echo "tests complete" | |
| echo "******************************************" | |
| echo "::endgroup::" |