Merge remote-tracking branch 'origin' into kylesayrs/cleanup-moe-examples

Author: kylesayrs

.github/actions/prepare-code-coverage/action.yml

@@ -0,0 +1,19 @@
+name: prepare code coverage
+description: installs code coverage dependencies and exports an updated 'PYTEST_ADDOPTS' env var
+
+runs:
+  using: composite
+  steps:
+    - run: |-
+        # install dependencies
+        pip3 install coverage pytest-cov https://github.com/neuralmagic/pytest-nm-releng/archive/v0.4.0.tar.gz
+
+        # generate and source flags
+        FLAGS_FILE="coverage_flags.sh"
+        nmre-generate-coverage-flags --package "llmcompressor" --output-file "$FLAGS_FILE"
+        source "$FLAGS_FILE"
+        rm "$FLAGS_FILE"
+
+        # export defined/updated 'PYTEST_ADDOPTS' env var
+        echo "PYTEST_ADDOPTS=$PYTEST_ADDOPTS" | tee -a "$GITHUB_ENV"
+      shell: bash

.github/workflows/test-check-transformers.yaml

@@ -1,10 +1,16 @@
 name: Test Checks (Transformers)
 on:
   pull_request:
-    branches: main
+    branches: [ main ]
     types: [ labeled, synchronize ]
   push:
-    branches: main
+    branches: [ main ]
+  workflow_dispatch:
+    inputs:
+      code_coverage:
+        description: if enabled, code coverage metrics will be collected during the test run
+        type: boolean
+        default: false
 
 env:
   CADENCE: "commit"
@@ -72,6 +78,9 @@ jobs:
           BUILD_TYPE=nightly pip3 install .
       - name: "Clean compressed-tensors directory"
         run: rm -r compressed-tensors/
+      - name: "⚙️ Prepare code coverage"
+        if: inputs.code_coverage
+        uses: ./.github/actions/prepare-code-coverage
       - name: "🔬 Running transformers tests"
         if: (success() || failure()) && steps.install.outcome == 'success'
         run: |
@@ -104,3 +113,18 @@ jobs:
         if: (success() || failure()) && steps.install.outcome == 'success'
         run: |
           pytest -v tests/llmcompressor/transformers/kv_cache
+      - name: "Upload coverage report"
+        if: (success() || failure()) && inputs.code_coverage
+        uses: actions/upload-artifact@v4
+        with:
+          name: transformers-tests-coverage-results
+          path: |
+            .coverage
+            coverage-html
+            coverage.json
+          include-hidden-files: true
+          retention-days: 5
+      - name: "Report coverage"
+        if: (success() || failure()) && inputs.code_coverage
+        run: |
+          coverage report --data-file=".coverage" --skip-empty --format="markdown" > "$GITHUB_STEP_SUMMARY"

.github/workflows/test-check.yaml

@@ -4,6 +4,12 @@ on:
     branches:
       - main
   push:
+  workflow_dispatch:
+    inputs:
+      code_coverage:
+        description: if enabled, code coverage metrics will be collected during the test run
+        type: boolean
+        default: false
 
 env:
   CADENCE: "commit"
@@ -12,6 +18,8 @@ jobs:
 
   base-tests:
     runs-on: ubuntu-22.04
+    env:
+      COVERAGE_FILE: ".coverage.base"
     steps:
       - uses: actions/setup-python@v5
         with:
@@ -36,11 +44,31 @@ jobs:
           BUILD_TYPE=nightly pip3 install .
       - name: "Clean compressed-tensors directory"
         run: rm -r compressed-tensors/
+      - name: "⚙️ Prepare code coverage"
+        if: inputs.code_coverage
+        uses: ./.github/actions/prepare-code-coverage
       - name: "🔬 Running base tests"
         run: make test
+      - name: "Upload coverage report"
+        if: (success() || failure()) && inputs.code_coverage
+        uses: actions/upload-artifact@v4
+        with:
+          name: base-tests-coverage-results
+          path: |
+            .coverage*
+            coverage-html
+            coverage.json
+          include-hidden-files: true
+          retention-days: 5
+      - name: "Report coverage"
+        if: (success() || failure()) && inputs.code_coverage
+        run: |
+          coverage report --data-file="$COVERAGE_FILE" --skip-empty --format="markdown" > "$GITHUB_STEP_SUMMARY"
 
   pytorch-tests:
     runs-on: ubuntu-22.04
+    env:
+      COVERAGE_FILE: ".coverage.pytorch"
     steps:
       - uses: actions/setup-python@v5
         with:
@@ -65,12 +93,32 @@ jobs:
           BUILD_TYPE=nightly pip3 install .
       - name: "Clean compressed-tensors directory"
         run: rm -r compressed-tensors/
+      - name: "⚙️ Prepare code coverage"
+        if: inputs.code_coverage
+        uses: ./.github/actions/prepare-code-coverage
       - name: "🔬 Running pytorch tests"
         run: |
           pytest -v tests/llmcompressor/pytorch
+      - name: "Upload coverage report"
+        if: (success() || failure()) && inputs.code_coverage
+        uses: actions/upload-artifact@v4
+        with:
+          name: pytorch-tests-coverage-results
+          path: |
+            .coverage*
+            coverage-html
+            coverage.json
+          include-hidden-files: true
+          retention-days: 5
+      - name: "Report coverage"
+        if: (success() || failure()) && inputs.code_coverage
+        run: |
+          coverage report --data-file="$COVERAGE_FILE" --skip-empty --format="markdown" > "$GITHUB_STEP_SUMMARY"
 
   compat-pytorch-1_9-pytorch-tests:
     runs-on: ubuntu-22.04
+    env:
+      COVERAGE_FILE: ".coverage.compat-pytorch-1.9"
     steps:
       - uses: actions/setup-python@v5
         with:
@@ -95,6 +143,71 @@ jobs:
           BUILD_TYPE=nightly pip3 install .
       - name: "Clean compressed-tensors directory"
         run: rm -r compressed-tensors/
+      - name: "⚙️ Prepare code coverage"
+        if: inputs.code_coverage
+        uses: ./.github/actions/prepare-code-coverage
       - name: "🔬 Running pytorch tests"
         run: |
           pytest -v tests/llmcompressor/pytorch
+      - name: "Upload coverage report"
+        if: (success() || failure()) && inputs.code_coverage
+        uses: actions/upload-artifact@v4
+        with:
+          name: compat-pytorch-tests-coverage-results
+          path: |
+            .coverage*
+            coverage-html
+            coverage.json
+          include-hidden-files: true
+          retention-days: 5
+      - name: "Report coverage"
+        if: (success() || failure()) && inputs.code_coverage
+        run: |
+          coverage report --data-file="$COVERAGE_FILE" --skip-empty --format="markdown" > "$GITHUB_STEP_SUMMARY"
+
+  combine-coverage:
+    runs-on: ubuntu-22.04
+    needs: [base-tests, pytorch-tests, compat-pytorch-1_9-pytorch-tests]
+    if: (success() || failure()) && inputs.code_coverage
+    steps:
+      - name: "Checkout llm-compressor"
+        uses: actions/checkout@v4
+
+      - name: "Download coverage artifacts"
+        uses: actions/download-artifact@v4
+        with:
+          merge-multiple: true
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+
+      - name: "Install dependencies"
+        run: |
+          pip3 install -U pip setuptools
+          pip3 install coverage setuptools-scm
+          make build  # need to build to generate the version.py file
+
+      - name: "Combine and report coverage"
+        run: |
+          cat << EOF > .coveragerc
+          [paths]
+          source =
+              src/
+              */site-packages/
+          EOF
+          coverage combine
+          coverage report --skip-empty --format="markdown" >> "$GITHUB_STEP_SUMMARY"
+          coverage html --directory coverage-html
+          coverage json -o coverage.json
+
+      - name: "Upload coverage report"
+        uses: actions/upload-artifact@v4
+        with:
+          name: combined-coverage-results
+          path: |
+            .coverage
+            coverage-html
+            coverage.json
+          include-hidden-files: true
+          retention-days: 5

.gitignore

@@ -53,6 +53,7 @@ wheels/
 .installed.cfg
 *.egg
 MANIFEST
+.cache/*
 
 # PyInstaller
 #  Usually these files are written by a python script from a template

.readthedocs.yaml

@@ -0,0 +1,22 @@
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the OS, Python version, and other tools you might need
+build:
+  os: ubuntu-24.04
+  tools:
+    python: "3.12"
+
+# Build documentation with Mkdocs
+mkdocs:
+   configuration: mkdocs.yml
+
+python:
+  install:
+    - method: pip
+      path: .
+      extra_requirements:
+        - dev

CODE_OF_CONDUCT.md

@@ -0,0 +1,77 @@
+# LLM Compressor Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our community a harassment-free experience for everyone, regardless of age, body size, visible or invisible disability, ethnicity, sex characteristics, gender identity and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, religion, or sexual identity and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming, diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our community include:
+
+- Demonstrating empathy and kindness toward other people
+- Being respectful of differing opinions, viewpoints, and experiences
+- Giving and gracefully accepting constructive feedback
+- Accepting responsibility and apologizing to those affected by our mistakes, and learning from the experience
+- Focusing on what is best not just for us as individuals, but for the overall community
+
+Examples of unacceptable behavior include:
+
+- The use of sexualized language or imagery, and sexual attention or advances of any kind
+- Trolling, insulting or derogatory comments, and personal or political attacks
+- Public or private harassment
+- Publishing others’ private information, such as a physical or email address, without their explicit permission
+- Other conduct which could reasonably be considered inappropriate in a professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of acceptable behavior and will take appropriate and fair corrective action in response to any behavior that they deem inappropriate, threatening, offensive, or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct, and will communicate reasons for moderation decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when an individual is officially representing the community in public spaces. Examples of representing our community include using an official e-mail address, posting via an official social media account, or acting as an appointed representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be reported to the community leaders responsible for enforcement through GitHub, Slack, or Email. All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing clarity around the nature of the violation and an explanation of why the behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, for a specified period of time. This includes avoiding interactions in community spaces as well as external channels like social media. Violating these terms may lead to a temporary or permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public communication with the community for a specified period of time. No public or private interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, is allowed during this period. Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community standards, including sustained inappropriate behavior, harassment of an individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 2.1, available at https://www.contributor-covenant.org/version/2/1/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla’s code of conduct enforcement ladder](https://github.com/mozilla/diversity).
+
+For answers to common questions about this code of conduct, see the FAQ at https://www.contributor-covenant.org/faq. Translations are available at https://www.contributor-covenant.org/translations.

README.md

@@ -18,11 +18,11 @@ Big updates have landed in LLM Compressor! To get a more in-depth look, check ou
 
 Some of the exciting new features include:
 
-* **Large Model Support with Sequential Onloading** As of llm-compressor>=0.6.0, you can now quantize very large language models on a single GPU. Models are broken into disjoint layers which are then onloaded to the GPU one layer at a time. For more information on sequential onloading, see [Big Modeling with Sequential Onloading](examples/big_models_with_sequential_onloading/README.md) as well as the [DeepSeek-R1 Example](examples/quantizing_moe/deepseek_r1_example.py).
+* **Llama4 Quantization Support**: Quantize a Llama4 model to [W4A16](examples/multimodal_vision/llama4_example.py) or [NVFP4](examples/quantization_w4a4_fp4/llama4_example.py). The checkpoint produced can seamlessly run in vLLM.
+* **Large Model Support with Sequential Onloading**: As of llm-compressor>=0.6.0, you can now quantize very large language models on a single GPU. Models are broken into disjoint layers which are then onloaded to the GPU one layer at a time. For more information on sequential onloading, see [Big Modeling with Sequential Onloading](examples/big_models_with_sequential_onloading/README.md) as well as the [DeepSeek-R1 Example](examples/quantizing_moe/deepseek_r1_example.py).
 * **Preliminary FP4 Quantization Support:** Quantize weights and activations to FP4 and seamlessly run the compressed model in vLLM. Model weights and activations are quantized following the NVFP4 [configuration](https://github.com/neuralmagic/compressed-tensors/blob/f5dbfc336b9c9c361b9fe7ae085d5cb0673e56eb/src/compressed_tensors/quantization/quant_scheme.py#L104). See examples of [weight-only quantization](examples/quantization_w4a16_fp4/llama3_example.py) and [fp4 activation support](examples/quantization_w4a4_fp4/llama3_example.py). Support is currently preliminary and additional support will be added for MoEs.
 * **Updated AWQ Support:** Improved support for MoEs with better handling of larger models
 * **Axolotl Sparse Finetuning Integration:** Seamlessly finetune sparse LLMs with our Axolotl integration. Learn how to create [fast sparse open-source models with Axolotl and LLM Compressor](https://developers.redhat.com/articles/2025/06/17/axolotl-meets-llm-compressor-fast-sparse-open). See also the [Axolotl integration docs](https://docs.axolotl.ai/docs/custom_integrations.html#llmcompressor).
-* **Day 0 Llama 4 Support:** Meta utilized LLM Compressor to create the [FP8-quantized Llama-4-Maverick-17B-128E](https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8), optimized for vLLM inference using [compressed-tensors](https://github.com/neuralmagic/compressed-tensors) format.
 
 ### Supported Formats
 * Activation Quantization: W8A8 (int8 and fp8)