NVIDIA/Model-OptimizerPublic

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.

AI summary: A unified library of state-of-the-art model optimization techniques for deep learning.

Stars
5.6K
+15 today
Forks
813
Watchers
33
Open issues
101
Open PRs
365
Contributors
~126
Commits
1.7K
Branches
475

PythonApache-2.0Created Apr 23, 2024Last push 3d agoLatest release 0.48.0+37 stars this week+274 this month

Quick answers

What is Model-Optimizer?
A unified library of state-of-the-art model optimization techniques for deep learning.
What does Model-Optimizer do?
NVIDIA Model Optimizer is a comprehensive library designed to compress and accelerate deep learning models for production deployment. It provides a unified interface for advanced optimization techniques, including quantization, distillation, and structural pruning. The library specifically prepares models for highly efficient execution on downstream frameworks like TensorRT and vLLM. By significantly reducing memory footprints and computational requirements, it maximizes inference speed on NVIDIA hardware.
Who is Model-Optimizer for?
This project is for machine learning engineers and researchers deploying models to production environments. It is essential for teams aiming to maximize GPU utilization and minimize inference latency.
How do I get started with Model-Optimizer?
https://nvidia.github.io/Model-Optimizer
How popular is Model-Optimizer on GitHub?
NVIDIA/Model-Optimizer has 5,616 stars and 813 forks on GitHub, and gained 37 stars in the last 7 days.
What license does Model-Optimizer use?
NVIDIA/Model-Optimizer is released under the Apache-2.0 license.

Star history

since Sep 24, 2026
02K4KSep 2026Oct 2026Oct 2026Nov 2026
5.6K stars as of Nov 17, 2026. Measured daily since Sep 24, 2026; GitHub no longer exposes earlier star timestamps.

Update history

1 recorded
  • Nov 10, 2026New release 0.48.0 (previously 0.47.0).

Contribution activity

commits per day, last 52 weeks
NovDecJanFebMarAprMayJunJulAugSepOctNovMonWedFri2025-11-16: 2 commits2025-11-17: 4 commits2025-11-18: 0 commits2025-11-19: 9 commits2025-11-20: 4 commits2025-11-21: 3 commits2025-11-22: 0 commits2025-11-23: 0 commits2025-11-24: 2 commits2025-11-25: 4 commits2025-11-26: 2 commits2025-11-27: 1 commit2025-11-28: 0 commits2025-11-29: 0 commits2025-11-30: 1 commit2025-12-01: 1 commit2025-12-02: 5 commits2025-12-03: 5 commits2025-12-04: 10 commits2025-12-05: 2 commits2025-12-06: 0 commits2025-12-07: 1 commit2025-12-08: 0 commits2025-12-09: 1 commit2025-12-10: 3 commits2025-12-11: 4 commits2025-12-12: 4 commits2025-12-13: 0 commits2025-12-14: 0 commits2025-12-15: 7 commits2025-12-16: 4 commits2025-12-17: 10 commits2025-12-18: 5 commits2025-12-19: 3 commits2025-12-20: 1 commit2025-12-21: 0 commits2025-12-22: 2 commits2025-12-23: 0 commits2025-12-24: 0 commits2025-12-25: 0 commits2025-12-26: 0 commits2025-12-27: 0 commits2025-12-28: 0 commits2025-12-29: 0 commits2025-12-30: 2 commits2025-12-31: 0 commits2026-01-01: 0 commits2026-01-02: 1 commit2026-01-03: 0 commits2026-01-04: 0 commits2026-01-05: 3 commits2026-01-06: 1 commit2026-01-07: 0 commits2026-01-08: 6 commits2026-01-09: 2 commits2026-01-10: 1 commit2026-01-11: 0 commits2026-01-12: 3 commits2026-01-13: 7 commits2026-01-14: 5 commits2026-01-15: 2 commits2026-01-16: 1 commit2026-01-17: 1 commit2026-01-18: 1 commit2026-01-19: 1 commit2026-01-20: 2 commits2026-01-21: 3 commits2026-01-22: 5 commits2026-01-23: 4 commits2026-01-24: 0 commits2026-01-25: 1 commit2026-01-26: 4 commits2026-01-27: 2 commits2026-01-28: 3 commits2026-01-29: 4 commits2026-01-30: 0 commits2026-01-31: 0 commits2026-02-01: 0 commits2026-02-02: 3 commits2026-02-03: 4 commits2026-02-04: 5 commits2026-02-05: 0 commits2026-02-06: 4 commits2026-02-07: 1 commit2026-02-08: 0 commits2026-02-09: 3 commits2026-02-10: 2 commits2026-02-11: 2 commits2026-02-12: 4 commits2026-02-13: 3 commits2026-02-14: 0 commits2026-02-15: 1 commit2026-02-16: 0 commits2026-02-17: 3 commits2026-02-18: 4 commits2026-02-19: 3 commits2026-02-20: 2 commits2026-02-21: 3 commits2026-02-22: 0 commits2026-02-23: 0 commits2026-02-24: 8 commits2026-02-25: 1 commit2026-02-26: 8 commits2026-02-27: 2 commits2026-02-28: 4 commits2026-03-01: 1 commit2026-03-02: 4 commits2026-03-03: 7 commits2026-03-04: 1 commit2026-03-05: 4 commits2026-03-06: 4 commits2026-03-07: 2 commits2026-03-08: 0 commits2026-03-09: 7 commits2026-03-10: 6 commits2026-03-11: 6 commits2026-03-12: 2 commits2026-03-13: 7 commits2026-03-14: 2 commits2026-03-15: 0 commits2026-03-16: 4 commits2026-03-17: 2 commits2026-03-18: 7 commits2026-03-19: 1 commit2026-03-20: 4 commits2026-03-21: 2 commits2026-03-22: 0 commits2026-03-23: 3 commits2026-03-24: 8 commits2026-03-25: 3 commits2026-03-26: 3 commits2026-03-27: 1 commit2026-03-28: 2 commits2026-03-29: 0 commits2026-03-30: 6 commits2026-03-31: 3 commits2026-04-01: 8 commits2026-04-02: 6 commits2026-04-03: 6 commits2026-04-04: 1 commit2026-04-05: 1 commit2026-04-06: 4 commits2026-04-07: 6 commits2026-04-08: 8 commits2026-04-09: 9 commits2026-04-10: 5 commits2026-04-11: 3 commits2026-04-12: 1 commit2026-04-13: 6 commits2026-04-14: 5 commits2026-04-15: 6 commits2026-04-16: 5 commits2026-04-17: 9 commits2026-04-18: 8 commits2026-04-19: 2 commits2026-04-20: 4 commits2026-04-21: 1 commit2026-04-22: 6 commits2026-04-23: 7 commits2026-04-24: 3 commits2026-04-25: 1 commit2026-04-26: 1 commit2026-04-27: 5 commits2026-04-28: 5 commits2026-04-29: 3 commits2026-04-30: 4 commits2026-05-01: 3 commits2026-05-02: 0 commits2026-05-03: 0 commits2026-05-04: 8 commits2026-05-05: 10 commits2026-05-06: 5 commits2026-05-07: 7 commits2026-05-08: 3 commits2026-05-09: 1 commit2026-05-10: 0 commits2026-05-11: 3 commits2026-05-12: 7 commits2026-05-13: 3 commits2026-05-14: 2 commits2026-05-15: 5 commits2026-05-16: 1 commit2026-05-17: 0 commits2026-05-18: 3 commits2026-05-19: 3 commits2026-05-20: 4 commits2026-05-21: 2 commits2026-05-22: 4 commits2026-05-23: 0 commits2026-05-24: 2 commits2026-05-25: 1 commit2026-05-26: 4 commits2026-05-27: 2 commits2026-05-28: 2 commits2026-05-29: 14 commits2026-05-30: 1 commit2026-05-31: 1 commit2026-06-01: 7 commits2026-06-02: 4 commits2026-06-03: 9 commits2026-06-04: 5 commits2026-06-05: 7 commits2026-06-06: 5 commits2026-06-07: 0 commits2026-06-08: 12 commits2026-06-09: 4 commits2026-06-10: 11 commits2026-06-11: 5 commits2026-06-12: 8 commits2026-06-13: 1 commit2026-06-14: 2 commits2026-06-15: 12 commits2026-06-16: 12 commits2026-06-17: 3 commits2026-06-18: 2 commits2026-06-19: 3 commits2026-06-20: 0 commits2026-06-21: 0 commits2026-06-22: 12 commits2026-06-23: 6 commits2026-06-24: 9 commits2026-06-25: 6 commits2026-06-26: 6 commits2026-06-27: 3 commits2026-06-28: 0 commits2026-06-29: 3 commits2026-06-30: 8 commits2026-07-01: 7 commits2026-07-02: 2 commits2026-07-03: 1 commit2026-07-04: 0 commits2026-07-05: 4 commits2026-07-06: 5 commits2026-07-07: 2 commits2026-07-08: 4 commits2026-07-09: 10 commits2026-07-10: 3 commits2026-07-11: 0 commits2026-07-12: 0 commits2026-07-13: 4 commits2026-07-14: 2 commits2026-07-15: 3 commits2026-07-16: 3 commits2026-07-17: 3 commits2026-07-18: 0 commits2026-07-19: 0 commits2026-07-20: 4 commits2026-07-21: 1 commit2026-07-22: 4 commits2026-07-23: 5 commits2026-07-24: 2 commits2026-07-25: 1 commit2026-07-26: 1 commit2026-07-27: 0 commits2026-07-28: 3 commits2026-07-29: 6 commits2026-07-30: 2 commits2026-07-31: 0 commits2026-08-01: 1 commit2026-08-02: 0 commits2026-08-03: 10 commits2026-08-04: 7 commits2026-08-05: 3 commits2026-08-06: 2 commits2026-08-07: 12 commits2026-08-08: 0 commits2026-08-09: 0 commits2026-08-10: 6 commits2026-08-11: 4 commits2026-08-12: 9 commits2026-08-13: 5 commits2026-08-14: 4 commits2026-08-15: 0 commits2026-08-16: 0 commits2026-08-17: 1 commit2026-08-18: 3 commits2026-08-19: 1 commit2026-08-20: 2 commits2026-08-21: 1 commit2026-08-22: 0 commits2026-08-23: 1 commit2026-08-24: 1 commit2026-08-25: 0 commits2026-08-26: 5 commits2026-08-27: 2 commits2026-08-28: 7 commits2026-08-29: 0 commits2026-08-30: 1 commit2026-08-31: 1 commit2026-09-01: 4 commits2026-09-02: 4 commits2026-09-03: 4 commits2026-09-04: 5 commits2026-09-05: 0 commits2026-09-06: 0 commits2026-09-07: 1 commit2026-09-08: 9 commits2026-09-09: 7 commits2026-09-10: 9 commits2026-09-11: 9 commits2026-09-12: 1 commit2026-09-13: 2 commits2026-09-14: 3 commits2026-09-15: 3 commits2026-09-16: 5 commits2026-09-17: 13 commits2026-09-18: 8 commits2026-09-19: 1 commit2026-09-20: 0 commits2026-09-21: 5 commits2026-09-22: 5 commits2026-09-23: 9 commits2026-09-24: 1 commit2026-09-25: 0 commits2026-09-26: 1 commit2026-09-27: 0 commits2026-09-28: 5 commits2026-09-29: 10 commits2026-09-30: 3 commits2026-10-01: 8 commits2026-10-02: 11 commits2026-10-03: 2 commits2026-10-04: 0 commits2026-10-05: 4 commits2026-10-06: 12 commits2026-10-07: 10 commits2026-10-08: 11 commits2026-10-09: 15 commits2026-10-10: 2 commits2026-10-11: 0 commits2026-10-12: 10 commits2026-10-13: 6 commits2026-10-14: 15 commits2026-10-15: 17 commits2026-10-16: 16 commits2026-10-17: 3 commits2026-10-18: 0 commits2026-10-19: 9 commits2026-10-20: 11 commits2026-10-21: 20 commits2026-10-22: 15 commits2026-10-23: 20 commits2026-10-24: 2 commits2026-10-25: 1 commit2026-10-26: 40 commits2026-10-27: 17 commits2026-10-28: 12 commits2026-10-29: 17 commits2026-10-30: 13 commits2026-10-31: 2 commits2026-11-01: 3 commits2026-11-02: 10 commits2026-11-03: 16 commits2026-11-04: 13 commits2026-11-05: 11 commits2026-11-06: 12 commits2026-11-07: 0 commits2026-11-08: 1 commit2026-11-09: 6 commits2026-11-10: 1 commit2026-11-11: 0 commits2026-11-12: 0 commits2026-11-13: 0 commits2026-11-14: 0 commits
1,434 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Very active

    1,434 commits in 52 weeks

  • Community-driven

    ~126 contributors

  • Well documented

    High community health score

  • Permissive license

    Apache-2.0

  • Continuous integration

    Automated checks passing

  • Repeat trending

    5 trending appearances

What Model-Optimizer does

NVIDIA Model Optimizer is a comprehensive library designed to compress and accelerate deep learning models for production deployment. It provides a unified interface for advanced optimization techniques, including quantization, distillation, and structural pruning. The library specifically prepares models for highly efficient execution on downstream frameworks like TensorRT and vLLM. By significantly reducing memory footprints and computational requirements, it maximizes inference speed on NVIDIA hardware.

This project is for machine learning engineers and researchers deploying models to production environments. It is essential for teams aiming to maximize GPU utilization and minimize inference latency.

  • Advanced quantization: Reduces model precision to drastically lower memory usage and increase throughput.
  • Structural pruning: Removes redundant parameters from neural networks to accelerate computation.
  • Knowledge distillation: Transfers knowledge from large, complex models to smaller, faster counterparts.
  • Deployment integration: Seamlessly exports optimized models to high-performance inference engines like TensorRT-LLM.
  • Unified API: Offers a single, consistent interface to apply multiple state-of-the-art optimization techniques.

Where teams use it

LLM deployment optimization

Quantize massive large language models to fit within restricted GPU VRAM limits for production serving.

Edge device inference

Prune and compress neural networks to run efficiently on resource-constrained edge hardware.

Latency reduction

Accelerate real-time inference speeds for computer vision and natural language processing applications.

Hardware utilization

Convert standard PyTorch models into highly optimized TensorRT engines to maximize GPU usage.

Getting started: https://nvidia.github.io/Model-Optimizer

README

main branch

Banner image

NVIDIA Model Optimizer

Documentation version license

Documentation | Roadmap | Announcement Blogs


NVIDIA Model Optimizer (referred to as Model Optimizer, or ModelOpt) is a library comprising state-of-the-art model optimization techniques including quantization, pruning, Neural Architecture Search (NAS), distillation, speculative decoding and sparsity to accelerate models.

[Input] Model Optimizer currently supports inputs of a Hugging Face, PyTorch or ONNX model.

[Optimize] Model Optimizer provides Python APIs for users to easily compose the above model optimization techniques and export an optimized quantized checkpoint. Model Optimizer is also integrated with NVIDIA Megatron-Bridge, Megatron-LM and Hugging Face Accelerate for training required inference optimization techniques.

[Export for deployment] Seamlessly integrated within the NVIDIA AI software ecosystem, the quantized checkpoint generated from Model Optimizer is ready for deployment in downstream inference frameworks like SGLang, TensorRT-LLM, TensorRT, or vLLM. The unified Hugging Face export API now supports both transformers and diffusers models.

Latest News

Previous News

Install

To install stable release packages for Model Optimizer with pip from PyPI:

pip install -U nvidia-modelopt[all]

Model Optimizer will download and install additional third-party open source software projects. Review the license terms of these open source projects before use.

To install from source in editable mode with all development dependencies or to use the latest features, run:

# Clone the Model Optimizer repository
git clone [email protected]:NVIDIA/Model-Optimizer.git
cd Model-Optimizer

pip install -e .[dev]

You can also directly use NVIDIA container images, which have Model Optimizer pre-installed:

  • nvcr.io/nvidia/pytorch:<version>-py3
  • nvcr.io/nvidia/nemo:<version>
  • nvcr.io/nvidia/tensorrt-llm/release:<version>

Before pulling and using the container images, please review their respective license terms. Make sure to upgrade Model Optimizer to the latest version as described above. Visit our installation guide for more fine-grained control on installed dependencies or for alternative docker images and environment variables to setup.

Techniques

Technique Description Getting started Examples
Post Training Quantization Compress model size by 2x-4x, speeding up inference while preserving model quality! [Start here] [HF LLMs / VLMs] [Megatron-Bridge LLMs / VLMs] [Diffusers] [ONNX] [Windows]
Quantization Aware Training / Distillation Refine accuracy of quantized models even further with a few training steps! [Start here] [Hugging Face] [Megatron-Bridge]
Pruning Reduce your model parameters or memory footprint and accelerate inference by removing unnecessary weights! [Start here] [General] [Megatron-Bridge]
Distillation Reduce deployment model size by teaching small models to behave like larger models! [Start here] [Hugging Face] [Megatron-Bridge] [Megatron-LM]
Speculative Decoding Train draft modules to predict extra tokens during inference! [Start here] [Hugging Face] [Megatron-LM]
Sparsity Efficiently compress your model by storing only its non-zero parameter values and their locations [Start here] [Hugging Face]

Pre-Quantized Checkpoints

Resources

Model Support Matrix

Model Type Support Matrix
LLM / VLM Quantization View Support Matrix
Diffusers Quantization View Support Matrix
ONNX Quantization View Support Matrix
Windows Quantization View Support Matrix
Quantization Aware Training View Support Matrix
Pruning View Support Matrix
Distillation View Support Matrix
Speculative Decoding View Support Matrix

Deprecation Policy

Model Optimizer follows a structured approach to managing deprecated features:

  • Communication: Deprecation notices are documented in the Changelog. Deprecated items include source code statements indicating deprecation timing, with runtime warnings issued upon use.
  • Migration Period: Since Model Optimizer is still pre-1.0, we provide a 1-release (~1-month) migration period after deprecation. During this window, deprecated features continue functioning while issuing warnings.
  • Scope: The policy addresses both complete deprecations (entire APIs removed) and partial ones (specific parameters removed while methods remain).
  • Removal: Following the migration period, deprecated elements are removed in alignment with semantic versioning standards, potentially including breaking changes in minor version updates while Model Optimizer remains in 0.x.

Citation

If you use NVIDIA Model Optimizer in your research, please cite it as follows:

@misc{nvidia-modelopt,
  author       = {{NVIDIA Corporation}},
  title        = {{NVIDIA Model Optimizer}},
  howpublished = {\url{https://github.com/NVIDIA/Model-Optimizer}},
  year         = {2024--2026},
  note         = {GitHub repository}
}

Contributing

Model Optimizer is now open source! We welcome any feedback, feature requests and PRs. Please read our Contributing guidelines for details on how to contribute to this project.

AI Agents

ModelOpt's agent skills can be installed from this repository and used in any workspace.

Claude Code

claude plugin marketplace add https://github.com/NVIDIA/Model-Optimizer.git
claude plugin install modelopt@modelopt

Codex

codex plugin marketplace add https://github.com/NVIDIA/Model-Optimizer.git

Then open /plugins, select the modelopt marketplace, and install modelopt. Contributors can also use the skills directly from a checkout. See the agent tooling notes.

Top Contributors

Contributors

Happy optimizing!

View on GitHub

Releases and announcements

56 total
  1. ModelOpt 0.47.1 Release0.47.1Nov 6, 2026

    ### Bug Fixes - Fix NVFP4 fake quantization (e.g. ``NVFP4_DEFAULT_CFG``) with Triton 3.9, as in the PyTorch 26.11 container, on GPUs with compute capability 8.9 or newer: it failed with ``NotImplementedError: Block pointers have been removed in favor of the tensor descriptor API``.

  2. 0.47.1rc00.47.1rc0Nov 5, 2026pre-release2 downloads

    -

  3. ModelOpt 0.48.0 Release0.48.0Nov 2, 202639 downloads

    ## New Features ### Sparsity - Add skip-softmax calibration through vLLM for FlashAttention and FlashInfer, requiring `--validation_prompts_file` and validating serving sparsity on calibration and held-out prompts before exporting prefill/decode fits and their validation scope as `sparse_attention_config`. Calibration uses single-sequence, unchunked eager execution; serving preserves the calibrated 128-token KV-tile granularity and 128-row prefill Q tiles, autotunes only its execution schedule, and uses a smaller Q tile for one-token decode. - Sparse-only vLLM installs now reject unsupported DCP, DBO/ubatching, speculative decoding, and FULL mixed-batch CUDA graphs; calibrated decode also rejects FULL decode graphs. ### Quantization - Add metadata-only export specifications and non-mutating per-weight quantizer-state capture. - Add functional quantized-weight packing, topology-aligned state merge/select and transport APIs, and canonical Hugging Face quantization-config construction. - HF export records canonical activation schemes, group/block sizes and weight-only MXFP4 metadata; mixed-format exports retain unquantized-layer exclusions, and non-square FP8 block layo

  4. 0.48.0rc20.48.0rc2Oct 28, 2026pre-release69 downloads

    Install this pre-release version using: ``` pip install "nvidia-modelopt[all] @ https://github.com/NVIDIA/Model-Optimizer/releases/download/0.48.0rc2/nvidia_modelopt-0.48.0rc2-py3-none-any.whl" ```

  5. 0.48.0rc10.48.0rc1Oct 17, 2026pre-release222 downloads

    Install this pre-release version using: ``` pip install "nvidia-modelopt[all] @ https://github.com/NVIDIA/Model-Optimizer/releases/download/0.48.0rc1/nvidia_modelopt-0.48.0rc1-py3-none-any.whl" ```

Code frequency

additions and deletions
+47K-47KWeek of 2025-11-16: +3,563 linesWeek of 2025-11-16: -2,139 linesWeek of 2025-11-23: +3,182 linesWeek of 2025-11-23: -1,451 linesWeek of 2025-11-30: +1,334 linesWeek of 2025-11-30: -796 linesWeek of 2025-12-07: +6,890 linesWeek of 2025-12-07: -3,382 linesWeek of 2025-12-14: +4,296 linesWeek of 2025-12-14: -2,519 linesWeek of 2025-12-21: +1,140 linesWeek of 2025-12-21: -3 linesWeek of 2025-12-28: +110 linesWeek of 2025-12-28: -27 linesWeek of 2026-01-04: +908 linesWeek of 2026-01-04: -564 linesWeek of 2026-01-11: +1,429 linesWeek of 2026-01-11: -350 linesWeek of 2026-01-18: +3,669 linesWeek of 2026-01-18: -890 linesWeek of 2026-01-25: +3,411 linesWeek of 2026-01-25: -447 linesWeek of 2026-02-01: +8,405 linesWeek of 2026-02-01: -2,061 linesWeek of 2026-02-08: +14,618 linesWeek of 2026-02-08: -5,071 linesWeek of 2026-02-15: +9,799 linesWeek of 2026-02-15: -1,512 linesWeek of 2026-02-22: +7,602 linesWeek of 2026-02-22: -758 linesWeek of 2026-03-01: +12,113 linesWeek of 2026-03-01: -3,356 linesWeek of 2026-03-08: +16,666 linesWeek of 2026-03-08: -5,718 linesWeek of 2026-03-15: +10,871 linesWeek of 2026-03-15: -2,684 linesWeek of 2026-03-22: +6,040 linesWeek of 2026-03-22: -3,608 linesWeek of 2026-03-29: +7,575 linesWeek of 2026-03-29: -681 linesWeek of 2026-04-05: +14,421 linesWeek of 2026-04-05: -9,870 linesWeek of 2026-04-12: +47,034 linesWeek of 2026-04-12: -6,820 linesWeek of 2026-04-19: +15,072 linesWeek of 2026-04-19: -11,125 linesWeek of 2026-04-26: +5,071 linesWeek of 2026-04-26: -961 linesWeek of 2026-05-03: +10,956 linesWeek of 2026-05-03: -2,573 linesWeek of 2026-05-10: +4,101 linesWeek of 2026-05-10: -3,868 linesWeek of 2026-05-17: +10,017 linesWeek of 2026-05-17: -2,616 linesWeek of 2026-05-24: +10,283 linesWeek of 2026-05-24: -3,576 linesWeek of 2026-05-31: +31,349 linesWeek of 2026-05-31: -16,264 linesWeek of 2026-06-07: +23,357 linesWeek of 2026-06-07: -3,455 linesWeek of 2026-06-14: +5,233 linesWeek of 2026-06-14: -1,065 linesWeek of 2026-06-21: +20,277 linesWeek of 2026-06-21: -11,008 linesWeek of 2026-06-28: +6,284 linesWeek of 2026-06-28: -1,686 linesWeek of 2026-07-05: +10,309 linesWeek of 2026-07-05: -1,415 linesWeek of 2026-07-12: +9,787 linesWeek of 2026-07-12: -6,907 linesWeek of 2026-07-19: +5,675 linesWeek of 2026-07-19: -2,538 linesWeek of 2026-07-26: +7,357 linesWeek of 2026-07-26: -187 linesWeek of 2026-08-02: +10,644 linesWeek of 2026-08-02: -1,509 linesWeek of 2026-08-09: +24,796 linesWeek of 2026-08-09: -16,073 linesWeek of 2026-08-16: +1,939 linesWeek of 2026-08-16: -1,159 linesWeek of 2026-08-23: +8,429 linesWeek of 2026-08-23: -1,866 linesWeek of 2026-08-30: +8,656 linesWeek of 2026-08-30: -3,233 linesWeek of 2026-09-06: +25,258 linesWeek of 2026-09-06: -7,757 linesWeek of 2026-09-13: +19,003 linesWeek of 2026-09-13: -7,496 linesWeek of 2026-09-20: +12,933 linesWeek of 2026-09-20: -3,389 linesWeek of 2026-09-27: +18,476 linesWeek of 2026-09-27: -3,741 linesWeek of 2026-10-04: +25,150 linesWeek of 2026-10-04: -11,341 linesWeek of 2026-10-11: +23,216 linesWeek of 2026-10-11: -2,168 linesWeek of 2026-10-18: +16,951 linesWeek of 2026-10-18: -5,723 linesWeek of 2026-10-25: +24,358 linesWeek of 2026-10-25: -4,540 linesWeek of 2026-11-01: +32,025 linesWeek of 2026-11-01: -3,608 linesWeek of 2026-11-08: +3,446 linesWeek of 2026-11-08: -1,028 linesNov 16, 2025Nov 8, 2026
+615.5K lines added, -198.6K removed over the last year.

Commits per week

last 52 weeks
1020Week of 2025-11-16: 22 commitsWeek of 2025-11-23: 9 commitsWeek of 2025-11-30: 24 commitsWeek of 2025-12-07: 13 commitsWeek of 2025-12-14: 30 commitsWeek of 2025-12-21: 2 commitsWeek of 2025-12-28: 3 commitsWeek of 2026-01-04: 13 commitsWeek of 2026-01-11: 19 commitsWeek of 2026-01-18: 16 commitsWeek of 2026-01-25: 14 commitsWeek of 2026-02-01: 17 commitsWeek of 2026-02-08: 14 commitsWeek of 2026-02-15: 16 commitsWeek of 2026-02-22: 23 commitsWeek of 2026-03-01: 23 commitsWeek of 2026-03-08: 30 commitsWeek of 2026-03-15: 20 commitsWeek of 2026-03-22: 20 commitsWeek of 2026-03-29: 30 commitsWeek of 2026-04-05: 36 commitsWeek of 2026-04-12: 40 commitsWeek of 2026-04-19: 24 commitsWeek of 2026-04-26: 21 commitsWeek of 2026-05-03: 34 commitsWeek of 2026-05-10: 21 commitsWeek of 2026-05-17: 16 commitsWeek of 2026-05-24: 26 commitsWeek of 2026-05-31: 38 commitsWeek of 2026-06-07: 41 commitsWeek of 2026-06-14: 34 commitsWeek of 2026-06-21: 42 commitsWeek of 2026-06-28: 21 commitsWeek of 2026-07-05: 28 commitsWeek of 2026-07-12: 15 commitsWeek of 2026-07-19: 17 commitsWeek of 2026-07-26: 13 commitsWeek of 2026-08-02: 34 commitsWeek of 2026-08-09: 28 commitsWeek of 2026-08-16: 8 commitsWeek of 2026-08-23: 16 commitsWeek of 2026-08-30: 19 commitsWeek of 2026-09-06: 36 commitsWeek of 2026-09-13: 35 commitsWeek of 2026-09-20: 21 commitsWeek of 2026-09-27: 39 commitsWeek of 2026-10-04: 54 commitsWeek of 2026-10-11: 67 commitsWeek of 2026-10-18: 77 commitsWeek of 2026-10-25: 102 commitsWeek of 2026-11-01: 65 commitsWeek of 2026-11-08: 8 commitsNov 16, 2025Nov 8, 2026
1.4K commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 2 commitsSun 1:00 — 0 commitsSun 2:00 — 2 commitsSun 3:00 — 1 commitsSun 4:00 — 2 commitsSun 5:00 — 3 commitsSun 6:00 — 0 commitsSun 7:00 — 1 commitsSun 8:00 — 0 commitsSun 9:00 — 4 commitsSun 10:00 — 1 commitsSun 11:00 — 4 commitsSun 12:00 — 1 commitsSun 13:00 — 2 commitsSun 14:00 — 1 commitsSun 15:00 — 0 commitsSun 16:00 — 1 commitsSun 17:00 — 1 commitsSun 18:00 — 1 commitsSun 19:00 — 0 commitsSun 20:00 — 1 commitsSun 21:00 — 2 commitsSun 22:00 — 4 commitsSun 23:00 — 2 commitsMon 0:00 — 0 commitsMon 1:00 — 0 commitsMon 2:00 — 3 commitsMon 3:00 — 0 commitsMon 4:00 — 3 commitsMon 5:00 — 0 commitsMon 6:00 — 2 commitsMon 7:00 — 1 commitsMon 8:00 — 4 commitsMon 9:00 — 11 commitsMon 10:00 — 29 commitsMon 11:00 — 20 commitsMon 12:00 — 23 commitsMon 13:00 — 29 commitsMon 14:00 — 26 commitsMon 15:00 — 19 commitsMon 16:00 — 28 commitsMon 17:00 — 14 commitsMon 18:00 — 16 commitsMon 19:00 — 7 commitsMon 20:00 — 11 commitsMon 21:00 — 16 commitsMon 22:00 — 17 commitsMon 23:00 — 22 commitsTue 0:00 — 16 commitsTue 1:00 — 11 commitsTue 2:00 — 9 commitsTue 3:00 — 9 commitsTue 4:00 — 3 commitsTue 5:00 — 2 commitsTue 6:00 — 1 commitsTue 7:00 — 0 commitsTue 8:00 — 6 commitsTue 9:00 — 19 commitsTue 10:00 — 12 commitsTue 11:00 — 24 commitsTue 12:00 — 20 commitsTue 13:00 — 24 commitsTue 14:00 — 29 commitsTue 15:00 — 20 commitsTue 16:00 — 27 commitsTue 17:00 — 19 commitsTue 18:00 — 13 commitsTue 19:00 — 9 commitsTue 20:00 — 10 commitsTue 21:00 — 16 commitsTue 22:00 — 15 commitsTue 23:00 — 11 commitsWed 0:00 — 18 commitsWed 1:00 — 14 commitsWed 2:00 — 12 commitsWed 3:00 — 4 commitsWed 4:00 — 4 commitsWed 5:00 — 3 commitsWed 6:00 — 0 commitsWed 7:00 — 3 commitsWed 8:00 — 5 commitsWed 9:00 — 13 commitsWed 10:00 — 21 commitsWed 11:00 — 17 commitsWed 12:00 — 26 commitsWed 13:00 — 24 commitsWed 14:00 — 30 commitsWed 15:00 — 36 commitsWed 16:00 — 17 commitsWed 17:00 — 17 commitsWed 18:00 — 15 commitsWed 19:00 — 6 commitsWed 20:00 — 4 commitsWed 21:00 — 11 commitsWed 22:00 — 16 commitsWed 23:00 — 18 commitsThu 0:00 — 15 commitsThu 1:00 — 8 commitsThu 2:00 — 13 commitsThu 3:00 — 6 commitsThu 4:00 — 4 commitsThu 5:00 — 4 commitsThu 6:00 — 3 commitsThu 7:00 — 2 commitsThu 8:00 — 5 commitsThu 9:00 — 19 commitsThu 10:00 — 21 commitsThu 11:00 — 26 commitsThu 12:00 — 20 commitsThu 13:00 — 23 commitsThu 14:00 — 15 commitsThu 15:00 — 22 commitsThu 16:00 — 19 commitsThu 17:00 — 12 commitsThu 18:00 — 11 commitsThu 19:00 — 11 commitsThu 20:00 — 10 commitsThu 21:00 — 13 commitsThu 22:00 — 22 commitsThu 23:00 — 15 commitsFri 0:00 — 9 commitsFri 1:00 — 8 commitsFri 2:00 — 4 commitsFri 3:00 — 2 commitsFri 4:00 — 1 commitsFri 5:00 — 0 commitsFri 6:00 — 1 commitsFri 7:00 — 2 commitsFri 8:00 — 5 commitsFri 9:00 — 15 commitsFri 10:00 — 18 commitsFri 11:00 — 27 commitsFri 12:00 — 22 commitsFri 13:00 — 22 commitsFri 14:00 — 28 commitsFri 15:00 — 28 commitsFri 16:00 — 26 commitsFri 17:00 — 18 commitsFri 18:00 — 18 commitsFri 19:00 — 10 commitsFri 20:00 — 4 commitsFri 21:00 — 11 commitsFri 22:00 — 12 commitsFri 23:00 — 18 commitsSat 0:00 — 11 commitsSat 1:00 — 8 commitsSat 2:00 — 3 commitsSat 3:00 — 3 commitsSat 4:00 — 4 commitsSat 5:00 — 2 commitsSat 6:00 — 2 commitsSat 7:00 — 0 commitsSat 8:00 — 0 commitsSat 9:00 — 3 commitsSat 10:00 — 4 commitsSat 11:00 — 5 commitsSat 12:00 — 3 commitsSat 13:00 — 2 commitsSat 14:00 — 1 commitsSat 15:00 — 2 commitsSat 16:00 — 0 commitsSat 17:00 — 5 commitsSat 18:00 — 4 commitsSat 19:00 — 2 commitsSat 20:00 — 3 commitsSat 21:00 — 3 commitsSat 22:00 — 3 commitsSat 23:00 — 2 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.
DateListRankStars gained
Sep 28, 2026daily#3+301
Sep 27, 2026daily#3+301
Sep 26, 2026daily#3+359
Sep 25, 2026daily#11+44
Sep 24, 2026daily#4+22