Sync Dev

.github/workflows/test-mlc-core-actions.yaml

@@ -0,0 +1,136 @@
+name: MLC core actions test
+
+on:
+  pull_request:
+    branches: [ "main", "dev" ]
+    paths:
+      - '.github/workflows/test-mlc-core-actions.yml'
+      - '**'
+      - '!**.md'
+
+jobs:
+  test_mlc_core_actions:
+
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.12", "3.8"]
+        os: ["ubuntu-latest", "windows-latest", "macos-latest"]
+        exclude:
+          - os: windows-latest
+          - os: macos-latest
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v3
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Configure git longpaths (Windows)
+      if: matrix.os == 'windows-latest'
+      run: |
+        git config --system core.longpaths true
+
+    - name: Install mlcflow from the pull request's source repository and branch
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install --ignore-installed --verbose pip setuptools
+        python -m pip install .
+
+    - name: Test 1 - pull repo - Pull a forked MLOps repository
+      run: |
+        GH_MLC_REPO_PATH_FORK="${HOME}/MLC/repos/anandhu-eng@mlperf-automations"
+        GH_MLC_REPO_JSON_PATH="${HOME}/MLC/repos/repos.json"
+        mlc pull repo anandhu-eng@mlperf-automations  --checkout=dev
+        if [ ! -d "${GH_MLC_REPO_PATH_FORK}" ]; then
+          echo "Repository folder $GH_MLC_REPO_PATH_FORK not found. Exiting with failure."
+          exit 1
+        fi
+        if [ ! -f "$GH_MLC_REPO_JSON_PATH" ]; then
+          echo "File $GH_MLC_REPO_JSON_PATH does not exist. Exiting with failure."
+          exit 1
+        fi
+        if ! grep -q "$GH_MLC_REPO_PATH_FORK" "$GH_MLC_REPO_JSON_PATH"; then
+          echo "Path $GH_MLC_REPO_PATH_FORK not found in $GH_MLC_REPO_JSON_PATH. Exiting with failure."
+          exit 1
+        fi
+        CURRENT_BRANCH=$(git -C "$GH_MLC_REPO_PATH_FORK" rev-parse --abbrev-ref HEAD)
+        if [ "$CURRENT_BRANCH" != "dev" ]; then
+          echo "Expected branch 'dev', but found '$CURRENT_BRANCH'. Exiting with failure."
+          exit 1
+        fi
+
+
+    - name: Test 2 - pull repo - Test conflicting repo scenario
+      run: |
+        GH_MLC_REPO_PATH="${HOME}/MLC/repos/mlcommons@mlperf-automations"
+        GH_MLC_REPO_JSON_PATH="${HOME}/MLC/repos/repos.json"
+        mlc pull repo mlcommons@mlperf-automations --checkout=dev
+        if [ ! -d "$GH_MLC_REPO_PATH" ]; then
+          echo "Repository folder $GH_MLC_REPO_PATH not found. Exiting with failure."
+          exit 1
+        fi
+        if [ ! -f "$GH_MLC_REPO_JSON_PATH" ]; then
+          echo "File $GH_MLC_REPO_JSON_PATH does not exist. Exiting with failure."
+          exit 1
+        fi
+        if ! grep -q "$GH_MLC_REPO_PATH" "$GH_MLC_REPO_JSON_PATH"; then
+          echo "Path $GH_MLC_REPO_PATH not found in $GH_MLC_REPO_JSON_PATH. Exiting with failure."
+          exit 1
+        fi
+        if ! grep -q "$GH_MLC_REPO_PATH_FORK" "$GH_MLC_REPO_JSON_PATH"; then
+          echo "Path $GH_MLC_REPO_PATH_FORK also found in $GH_MLC_REPO_JSON_PATH. This should have been replaced. Exiting with failure."
+          exit 1
+        fi
+        CURRENT_BRANCH=$(git -C "$GH_MLC_REPO_PATH" rev-parse --abbrev-ref HEAD)
+        if [ "$CURRENT_BRANCH" != "dev" ]; then
+          echo "Expected branch 'dev', but found '$CURRENT_BRANCH'. Exiting with failure."
+          exit 1
+        fi
+
+    - name: Test 3 - list repo - List the existing repositories
+      run: |
+        mlc list repo
+
+    - name: Test  4 - rm repo - Remove the forked mlperf-automation repo
+      run: |
+        GH_MLC_REPO_PATH_FORK="${HOME}/MLC/repos/anandhu-eng@mlperf-automations"
+        mlc rm repo anandhu-eng@mlperf-automations
+        if [ -d "$GH_MLC_REPO_PATH_FORK" ]; then
+          echo "Repository folder $GH_MLC_REPO_PATH found. It should ideally be deleted. Exiting with failure."
+          exit 1
+        fi
+
+    - name: Test 5 - find cache - Cache not present
+      run: |
+        mlc find cache --tags=detect,os 2>&1 | tee test5.log
+        if ! grep -q "No cache entry found for the specified tags:" test5.log; then
+          exit 1
+        fi
+
+    - name: Test 6 - run script - Output being used for testing mlc cache
+      run: |
+        mlc run script --tags=get,imagenet-aux --quiet
+        mlc run script --tags=get,imagenet-aux,_from.dropbox --quiet
+
+    - name: Test 7 - find cache - More than one cache present
+      run: |
+        mlc search cache --tags=get,imagenet-aux 2>&1 | tee test7.log
+        if grep -q "No cache entry found for the specified tags:" test7.log; then
+          exit 1
+        fi
+
+    - name: Test 8 - show cache - More than one cache present
+      run: |
+        mlc show cache --tags=get,imagenet-aux 2>&1 | tee test7.log
+
+    - name: Test 9 - rm cache - More than one cache present
+      run: |
+        mlc rm cache --tags=get,imagenet-aux 2>&1 --all | tee test7.log
+
+    - name: Test 10 - cp script - Copy mlc script 
+      run: |
+        mlc cp script detect-os my-os-detect
+

CONTRIBUTORS.md

@@ -28,14 +28,10 @@ Once your contribution exceeds 50 lines of code (in total), we will:
 
 ## Current Contributors
 
-- **[Arjun Suresh]** - *Initial Development*  
-- **[Anandhu Sooraj]** - *Initial Development*  
-- **[Shaik Masthan]** - *Initial Development*  
-- **[Sahil Avaran]** - *Initial Development*, added logging  
-- **[Ayushi Chaudhari]** - *Initial Development*  
-- **[Contributor 1]** - Added core features for CLI workflow.  
-- **[Contributor 2]** - Refactored caching system and enhanced performance.  
-- **[Contributor 3]** - Improved documentation and code structure.  
+- **[Arjun Suresh]** - *Initial Development Discussions, {Script,Cache} Action implementations*  
+- **[Anandhu Sooraj]** - *Initial Development Discussions, RepoAction implmentation, Github Tests*  
+- **[Shaik Masthan]** - *Initial Development Discussions*  
+- **[Sahil Avaran]** - *Initial Development Discussions*, added logging  
 - **[Your Name Here]** - This could be you! 🎉  
 
 ---

README.md

@@ -1,18 +1,25 @@
 **MLCFlow: Simplifying MLPerf Automations**
 
+[![License](https://img.shields.io/badge/License-Apache%202.0-green)](LICENSE.md)
+[![Downloads](https://static.pepy.tech/badge/mlcflow)](https://pepy.tech/project/mlcflow)
+
+[![MLC core actions test](https://github.com/mlcommons/mlcflow/actions/workflows/test-mlc-core-actions.yaml/badge.svg)](https://github.com/mlcommons/mlcflow/actions/workflows/test-mlc-core-actions.yaml)
+[![MLC script automation features test](https://github.com/mlcommons/mlperf-automations/actions/workflows/test-mlc-script-features.yml/badge.svg?cache-bust=1)](https://github.com/mlcommons/mlperf-automations/actions/workflows/test-mlc-script-features.yml)
+[![MLPerf inference resnet50](https://github.com/mlcommons/mlcflow/actions/workflows/mlperf-inference-resnet50.yml/badge.svg)](https://github.com/mlcommons/mlcflow/actions/workflows/mlperf-inference-resnet50.yml)
+[![MLPerf inference bert (deepsparse, tf, onnxruntime, pytorch)](https://github.com/mlcommons/mlcflow/actions/workflows/mlperf-inference-bert.yml/badge.svg)](https://github.com/mlcommons/mlcflow/actions/workflows/mlperf-inference-bert.yml)
+
+
 MLCFlow is a versatile CLI and Python interface developed by MLCommons in collaboration with a dedicated team of volunteers (see [Contributors](CONTRIBUTORS.md)). It serves as a streamlined replacement for the [CMind](https://github.com/mlcommons/ck/tree/master/cm) tool, designed to drive the automation workflows of MLPerf benchmarks more efficiently. 
 
 The concept behind CMind originated from **Grigori Fursin**, while the **MLPerf Automations** project was created by **Grigori Fursin** and **Arjun Suresh**, whose collective contributions laid the foundation for modernizing MLPerf benchmarking tools.
 
 ### Key Features
 Building upon the core idea of CMind—wrapping native scripts with Python wrappers and YAML metadata—MLCFlow focuses exclusively on key automation components: **Scripts**, along with its complementary modules: **Cache**, **Docker**, and **Experiments**. This targeted design simplifies both implementation and interface, enabling a more user-friendly experience.
 
-### Status
-MLCFlow is currently a **work in progress** and not yet ready for production use. If you are interested in contributing to its initial development, please email [[email protected]](mailto:[email protected]) to join the daily development meetings and see [Issues](https://github.com/mlcommons/mlcflow/issues) for seeing the development progress.
-
-### Getting Started
-For early contributors, please use the `mlc` branch of the [MLPerf Automations](https://github.com/mlcommons/mlperf-automations) repository while working with MLCFlow.
+---
 
+### Status
+MLCFlow is now fully equipped for workflow development, with complete support for all previously used CM scripts in MLPerf inference automation. If you're interested in discussions, join the MLCommons Benchmark Infra [Discord channel](https://discord.gg/T9rHVwQFNX), and check out the latest progress in [Issues](https://github.com/mlcommons/mlcflow/issues).
 
 ---
 
@@ -42,38 +49,65 @@ mlc <action> <target> [options]
 #### 3. **Cache**
 - Handle cached data, including cleanup or inspection.
 
-Each target has its own set of specific actions to tailor automation workflows.
+Each target has its own set of specific actions to tailor automation workflows as specified below.
+
+
+
+| Target | Action          |
+|--------|-----------------|
+| script    | run, search, rm, mv, cp, add, list, test, docker, show          |
+| cache    | search, rm, list, show, find          |
+| repo    | pull, search, rm, list, find          |
+
 
 ## CM compatibility layer
 
-MLC has a compatibility layer where by it supports MLCommons CM automations - Script, Cache and Experiment. 
+MLC started with a compatibility layer where by it supported MLCommons CM automations - Script, Cache and Experiment. Now, MLCFLow has just the Script Automation which is an extension of the Script Automation from CM but with a cleaner integration of Cache Automation and Docker and Test extensions. The old CM scripts are now updated with the latest MLCFlow scripts in the [MLPerf Automations](https://github.com/mlcommons/mlperf-automations/tree/main/script) repository. 
 
 ## Architectural Diagram
 
 ```mermaid
 classDiagram
     class Action {
-        -repos_path : str
-        -cfg : dict
-        -repos : list
-        +execute(args)
         +access(options)
-        +asearch(i)
         +find_target_folder(target)
         +load_repos_and_meta()
         +load_repos()
+        +conflicting_repo(repo_meta)
+        +register_repo(repo_meta)
+        +unregister_repo(repo_path)
+        +add(i)
+        +rm(i)
+        +save_new_meta(i, item_id, item_name, target_name, item_path, repo)
+        +update(i)
+        +is_uid(name)
+        +cp(run_args)
+        +copy_item(source_path, destination_path)
+        +search(i)
     }
     class RepoAction {
+        +find(run_args)
         +github_url_to_user_repo_format(url)
-        +pull(args)
-        +list(args)
+        +pull_repo(repo_url, branch, checkout)
+        +pull(run_args)
+        +list(run_args)
+        +rm(run_args)
     }
     class ScriptAction {
-        +run(args)
+        +search(i)
+        +rm(i)
+        +dynamic_import_module(script_path)
+        +call_script_module_function(function_name, run_args)
+        +docker(run_args)
+        +run(run_args)
+        +test(run_args)
         +list(args)
     }
     class CacheAction {
-        +show(args)
+        +search(i)
+        +find(i)
+        +rm(i)
+        +show(run_args)
         +list(args)
     }
     class ExperimentAction {
@@ -82,38 +116,47 @@ classDiagram
     }
     class CfgAction {
         +load(args)
-        +unload(args)
+    }
+    class Index {
+        +add(meta, folder_type, path, repo)
+        +get_index(folder_type, uid)
+        +update(meta, folder_type, path, repo)
+        +rm(meta, folder_type, path)
+        +build_index()
+    }
+    class Item {
+        +meta
+        +path
+        +repo
+        +_load_meta()
     }
     class Repo {
-        -path : str
-        -meta : dict
+        +path
+        +meta
+        +_load_meta()
     }
     class Automation {
-        -cmind : Action
-        +execute(args)
-    }
-    class Index {
-        +find()
+        +action_object
+        +automation_type
+        +meta
+        +path
+        +_load_meta()
+        +search(i)
     }
 
     Action <|-- RepoAction
     Action <|-- ScriptAction
     Action <|-- CacheAction
     Action <|-- ExperimentAction
     Action <|-- CfgAction
-    Repo "1" *-- Action
-    Automation "1" *-- Action
-
-    class get_action {
-        +actions : dict
-        +get_action(target)
-    }
-
-    main --> get_action
-    get_action --> RepoAction
-    get_action --> ScriptAction
-    get_action --> CacheAction
-    get_action --> ExperimentAction
-    get_action --> CfgAction
+    RepoAction o-- Repo
+    ScriptAction o-- Automation
+    CacheAction o-- Index
+    ExperimentAction o-- Index
+    CfgAction o-- Index
+    Index o-- Repo
+    Index o-- Item
+    Item o-- Repo
+    Automation o-- Action
 ```