publish ci (microsoft#17)

.github/workflows/publish.yml

@@ -0,0 +1,111 @@
+# this workflow is refered from vllm/.github/workflows/publish.yml
+# This workflow will upload a Python Package to Release asset
+# For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: Create Release
+
+on:
+  push:
+    tags:
+      - v*
+
+# Needed to create release and upload assets
+permissions:
+  contents: write
+
+jobs:
+  release:
+    # Retrieve tag and create release
+    name: Create Release
+    runs-on: ubuntu-latest
+    outputs:
+      upload_url: ${{ steps.create_release.outputs.upload_url }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - name: Extract branch info
+        shell: bash
+        run: |
+          echo "release_tag=${GITHUB_REF#refs/*/}" >> $GITHUB_ENV
+
+      - name: Create Release
+        id: create_release
+        uses: "actions/github-script@v6"
+        env:
+          RELEASE_TAG: ${{ env.release_tag }}
+        with:
+          github-token: "${{ secrets.GITHUB_TOKEN }}"
+          script: |
+            const script = require('.github/workflows/scripts/create_release.js')
+            await script(github, context, core)
+
+  wheel:
+    name: Build Wheel
+    runs-on: ${{ matrix.os }}
+    needs: release
+
+    strategy:
+      fail-fast: false
+      matrix:
+          os: ['ubuntu-20.04']
+          python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
+          pytorch-version: ['2.4.0']  # Must be the most recent version that meets requirements-cuda.txt.
+          cuda-version: ['12.1']
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - name: Setup ccache
+        uses: hendrikmuhs/[email protected]
+        with:
+          create-symlink: true
+          key: ${{ github.job }}-${{ matrix.python-version }}-${{ matrix.cuda-version }}
+
+      - name: Set up Linux Env
+        if: ${{ runner.os == 'Linux' }}
+        run: |
+          bash -x .github/workflows/scripts/env.sh
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+            python-version: ${{ matrix.python-version }}
+
+      - name: Install CUDA ${{ matrix.cuda-version }}
+        run: |
+          bash -x .github/workflows/scripts/cuda-install.sh ${{ matrix.cuda-version }} ${{ matrix.os }}
+
+      - name: Install PyTorch ${{ matrix.pytorch-version }} with CUDA ${{ matrix.cuda-version }}
+        run: |
+          bash -x .github/workflows/scripts/pytorch-install.sh ${{ matrix.python-version }} ${{ matrix.pytorch-version }} ${{ matrix.cuda-version }}
+
+      - name: Build wheel
+        shell: bash
+        env:
+          CMAKE_BUILD_TYPE: Release # do not compile with debug symbol to reduce wheel size
+        run: |
+          bash -x .github/workflows/scripts/build.sh ${{ matrix.python-version }} ${{ matrix.cuda-version }}
+          wheel_name=$(ls dist/*whl | xargs -n 1 basename)
+          asset_name=${wheel_name//"linux"/"manylinux1"}
+          echo "wheel_name=${wheel_name}" >> $GITHUB_ENV
+          echo "asset_name=${asset_name}" >> $GITHUB_ENV
+
+      - name: Upload Release Asset
+        uses: actions/upload-release-asset@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          upload_url: ${{ needs.release.outputs.upload_url }}
+          asset_path: ./dist/${{ env.wheel_name }}
+          asset_name: ${{ env.asset_name }}
+          asset_content_type: application/*
+
+      # (Danielkinz): This last step will publish the .whl to pypi. Warning: untested
+      # - name: Publish package
+      #   uses: pypa/gh-action-pypi-publish@release/v1.8
+      #   with:
+      #     repository-url: https://test.pypi.org/legacy/
+      #     password: ${{ secrets.PYPI_API_TOKEN }}
+      #     skip-existing: true

.github/workflows/scripts/build.sh

@@ -0,0 +1,19 @@
+#!/bin/bash
+
+python_executable=python$1
+cuda_home=/usr/local/cuda-$2
+
+# Update paths
+PATH=${cuda_home}/bin:$PATH
+LD_LIBRARY_PATH=${cuda_home}/lib64:$LD_LIBRARY_PATH
+
+# Install requirements
+$python_executable -m pip install wheel packaging
+$python_executable -m pip install -r requirements-cuda.txt
+
+# Limit the number of parallel jobs to avoid OOM
+export MAX_JOBS=1
+# Make sure release wheels are built for the following architectures
+export TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 8.9 9.0+PTX"
+# Build
+$python_executable setup.py bdist_wheel --dist-dir=dist

.github/workflows/scripts/create_release.js

@@ -0,0 +1,20 @@
+// Uses Github's API to create the release and wait for result.
+// We use a JS script since github CLI doesn't provide a way to wait for the release's creation and returns immediately.
+
+module.exports = async (github, context, core) => {
+	try {
+		const response = await github.rest.repos.createRelease({
+			draft: false,
+			generate_release_notes: true,
+			name: process.env.RELEASE_TAG,
+			owner: context.repo.owner,
+			prerelease: true,
+			repo: context.repo.repo,
+			tag_name: process.env.RELEASE_TAG,
+		});
+
+		core.setOutput('upload_url', response.data.upload_url);
+	} catch (error) {
+		core.setFailed(error.message);
+	}
+}

.github/workflows/scripts/cuda-install.sh

@@ -0,0 +1,23 @@
+#!/bin/bash
+
+# Replace '.' with '-' ex: 11.8 -> 11-8
+cuda_version=$(echo $1 | tr "." "-")
+# Removes '-' and '.' ex: ubuntu-20.04 -> ubuntu2004
+OS=$(echo $2 | tr -d ".\-")
+
+# Installs CUDA
+wget -nv https://developer.download.nvidia.com/compute/cuda/repos/${OS}/x86_64/cuda-keyring_1.1-1_all.deb
+sudo dpkg -i cuda-keyring_1.1-1_all.deb
+rm cuda-keyring_1.1-1_all.deb
+sudo apt -qq update
+sudo apt -y install cuda-${cuda_version} cuda-nvcc-${cuda_version} cuda-libraries-dev-${cuda_version}
+sudo apt clean
+
+# Test nvcc
+PATH=/usr/local/cuda-$1/bin:${PATH}
+nvcc --version
+
+# Log gcc, g++, c++ versions
+gcc --version
+g++ --version
+c++ --version

.github/workflows/scripts/env.sh

@@ -0,0 +1,56 @@
+#!/bin/bash
+
+# This file installs common linux environment tools
+
+export LANG C.UTF-8
+
+# python_version=$1
+
+sudo    apt-get update && \
+sudo    apt-get install -y --no-install-recommends \
+        software-properties-common \
+
+sudo    apt-get install -y --no-install-recommends \
+        build-essential \
+        apt-utils \
+        ca-certificates \
+        wget \
+        git \
+        vim \
+        libssl-dev \
+        curl \
+        unzip \
+        unrar \
+        cmake \
+        net-tools \
+        sudo \
+        autotools-dev \
+        rsync \
+        jq \
+        openssh-server \
+        tmux \
+        screen \
+        htop \
+        pdsh \
+        openssh-client \
+        lshw \
+        dmidecode \
+        util-linux \
+        automake \
+        autoconf \
+        libtool \
+        net-tools \
+        pciutils \
+        libpci-dev \
+        libaio-dev \
+        libcap2 \
+        libtinfo5 \
+        fakeroot \
+        devscripts \
+        debhelper \
+        nfs-common
+
+# Remove github bloat files to free up disk space
+sudo rm -rf "/usr/local/share/boost"
+sudo rm -rf "$AGENT_TOOLSDIRECTORY"
+sudo rm -rf "/usr/share/dotnet"

.github/workflows/scripts/pytorch-install.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+
+python_executable=python$1
+pytorch_version=$2
+cuda_version=$3
+
+# Install torch
+$python_executable -m pip install numpy pyyaml scipy ipython mkl mkl-include ninja cython typing pandas typing-extensions dataclasses setuptools && conda clean -ya
+$python_executable -m pip install torch==${pytorch_version}+cu${cuda_version//./} --extra-index-url https://download.pytorch.org/whl/cu${cuda_version//./}
+
+# Print version information
+$python_executable --version
+$python_executable -c "import torch; print('PyTorch:', torch.__version__)"
+$python_executable -c "import torch; print('CUDA:', torch.version.cuda)"
+$python_executable -c "from torch.utils import cpp_extension; print (cpp_extension.CUDA_HOME)"

format.sh

@@ -1 +1,4 @@
 yapf  --recursive . --style='{based_on_style: google, column_limit: 120, indent_width: 4}' -i
+isort .
+find csrc/ \( -name '*.h' -o -name '*.cc' -o -name '*.cu' -o -name '*.cuh' \) -print \
+| xargs clang-format -i

pyproject.toml

@@ -1,5 +1,5 @@
 [build-system]
-# Should be mirrored in requirements-build.txt
+# Should be mirrored in requirements.txt
 requires = [
     "packaging",
     "setuptools >= 49.4.0",

requirements.txt

@@ -1,6 +1,6 @@
 datasets
 torch
-transformers
+transformers>=4.44
 safetensors
 psutil
 accelerate

vptq/__init__.py

@@ -4,4 +4,4 @@
 # --------------------------------------------------------------------------
 
 __version__ = "0.0.1"
-from .layers.model_base import AutoModelForCausalLM as AutoModelForCausalLM
+from .layers import AutoModelForCausalLM as AutoModelForCausalLM

vptq/app.py

@@ -1,3 +1,8 @@
+# -------------------------------------------------------------------------
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License.
+# --------------------------------------------------------------------------
+
 import os
 
 import gradio as gr

vptq/layers/__init__.py

@@ -0,0 +1,6 @@
+# -------------------------------------------------------------------------
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License.
+# --------------------------------------------------------------------------
+
+from .model_base import AutoModelForCausalLM as AutoModelForCausalLM