This is an automated email from the ASF dual-hosted git repository. guanmingchiu pushed a commit to branch main in repository https://gitbox.apache.org/repos/asf/mahout.git
commit 3c174ed2f6be1adc6c0377f8a4ecdd72ab486de1 Author: Ryan Huang <[email protected]> AuthorDate: Fri Dec 26 10:12:29 2025 +0800 [QDP] Add colab benchmark example (#755) * colab benchmark * add link * add link * update with colab badge * precommit * renamed folder name to notebooks * update link --- qdp/benchmark/README.md | 6 + qdp/benchmark/notebooks/mahout_benchmark.ipynb | 207 +++++++++++++++++++++++++ 2 files changed, 213 insertions(+) diff --git a/qdp/benchmark/README.md b/qdp/benchmark/README.md new file mode 100644 index 000000000..e338d2545 --- /dev/null +++ b/qdp/benchmark/README.md @@ -0,0 +1,6 @@ +<!-- TODO: benchmark docs --> + + +### We can also run benchmarks on colab notebooks(without owning a GPU) + +[](https://colab.research.google.com/github/apache/mahout/blob/colab-benchmark/qdp/benchmark/notebooks/mahout_benchmark.ipynb) diff --git a/qdp/benchmark/notebooks/mahout_benchmark.ipynb b/qdp/benchmark/notebooks/mahout_benchmark.ipynb new file mode 100644 index 000000000..81fd746fd --- /dev/null +++ b/qdp/benchmark/notebooks/mahout_benchmark.ipynb @@ -0,0 +1,207 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "pjstUzDHQHad" + }, + "source": [ + "## Install environments" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/"; + }, + "collapsed": true, + "id": "-hkLubLFXs_8", + "outputId": "95dda2d2-2cff-4b99-8a19-ce47e6f67fa6" + }, + "outputs": [], + "source": [ + "!sudo apt-get update -y > /dev/null\n", + "!sudo apt-get install python3.11 python3.11-dev python3.11-distutils libpython3.11-dev > /dev/null\n", + "!sudo apt-get install python3.11-venv binfmt-support > /dev/null\n", + "!sudo apt-get install python3-pip > /dev/null\n", + "!python3 -m pip install --upgrade pip > /dev/null\n", + "!python3 -m pip install ipykernel\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/"; + }, + "collapsed": true, + "id": "_HEpQ4F3C4gV", + "outputId": "2f9969f4-313b-4652-ddf8-e538598532db" + }, + "outputs": [], + "source": [ + "# 1. Install Rust Toolchain\n", + "!curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y\n", + "import os\n", + "os.environ['PATH'] += \":/root/.cargo/bin\"\n", + "\n", + "# 2. Verify Installation\n", + "!rustc --version\n", + "!cargo --version\n", + "\n", + "# 3. Install Maturin (Build Backend for qdp-python)\n", + "!pip install maturin" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/"; + }, + "collapsed": true, + "id": "ljkluVL5ES4S", + "outputId": "73b1d5c1-6580-4633-e774-f58a138e94b8" + }, + "outputs": [], + "source": [ + "!curl -LsSf https://astral.sh/uv/install.sh | sh" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/"; + }, + "id": "9cgMNKOoEgYm", + "outputId": "24cec148-17c9-4dea-c47f-18d05e6b1911" + }, + "outputs": [], + "source": [ + "!nvcc --version\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "rOja7HAaQL1h" + }, + "source": [ + "## Install Mahout" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/"; + }, + "collapsed": true, + "id": "u7Skxs7lDBlq", + "outputId": "ff876484-54a0-4f92-ca9b-ff7003997ee6" + }, + "outputs": [], + "source": [ + "# 1. Clone the repository\n", + "!git clone -b dev-qdp https://github.com/apache/mahout.git\n";, + "\n", + "# 2. Install Python Dependencies\n", + "# We use the requirements file provided in the benchmark folder\n", + "%cd /content/mahout/qdp/qdp-python\n", + "!uv venv -p python3.11\n", + "# Activate the virtual environment and run uv sync and maturin develop\n", + "!source .venv/bin/activate && uv sync --group dev\n", + "# !source .venv/bin/activate && uv run --python 3.11 maturin develop" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "XX7w2efnD9np" + }, + "outputs": [], + "source": [ + "%cd /content/mahout/qdp/qdp-python\n", + "\n", + "# 1. Remove all old wheels to prevent future conflicts\n", + "!rm -rf /content/mahout/qdp/target/wheels/*\n", + "\n", + "# 2. Re-run build (so we have exactly one fresh wheel)\n", + "!uv run maturin build --interpreter .venv/bin/python\n", + "\n", + "# 3. Install the single new wheel found\n", + "!uv pip install /content/mahout/qdp/target/wheels/*.whl --python .venv/bin/python --force-reinstall\n", + "\n", + "!./.venv/bin/python -c \"import mahout_qdp; print(mahout_qdp.__file__)\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true, + "id": "eYLNNzRQFNQ_" + }, + "outputs": [], + "source": [ + "!uv pip install -r /content/mahout/qdp/benchmark/requirements.txt --python .venv/bin/python" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true, + "id": "qqmfUHGsGm8m" + }, + "outputs": [], + "source": [ + "!uv pip install matplotlib-inline --python .venv/bin/python" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "hj7sU3yJQeMj" + }, + "source": [ + "## Run Benchmarks" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "iuP5BdI3E-oR" + }, + "outputs": [], + "source": [ + "!./.venv/bin/python /content/mahout/qdp/benchmark/benchmark_e2e.py --frameworks mahout-parquet mahout-arrow pennylane --qubits 18 --samples 500" + ] + } + ], + "metadata": { + "accelerator": "GPU", + "colab": { + "gpuType": "T4", + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3", + "name": "python3" + }, + "language_info": { + "name": "python" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +}
