kvquant


Namekvquant JSON
Version 0.0.1 PyPI version JSON
download
home_pageNone
SummaryMore for Keys, Less for Values: Adaptive KV Cache Quantization 🐍🚀🎉🦕
upload_time2025-02-27 20:12:37
maintainerNone
docs_urlNone
authorNone
requires_python>=3.10
licenseGPL-3.0 License
keywords large language models cache quantization compression optimization
VCS
bugtrack_url
requirements No requirements were recorded.
Travis-CI No Travis.
coveralls test coverage No coveralls.
            ==============
kvq
==============

More for Keys, Less for Values: Adaptive KV Cache Quantization ☝️🔑👇🔢


Installation
------------

To install the package, use pip:

.. code-block:: bash

    pip install kvq


Usage
-----

To use the package, import it in your Python code:

.. code-block:: python

    import kvq

    medviz.layered_plot(image_path="dataset/1-1.nii", mask_paths=["dataset/small_bowel.nii", "dataset/1-1-label.nii"], mask_colors=["red", "yellow"], title="Layered Plot")

The `layered_plot` function creates a layered plot of an image and one or more masks. The masks are overlaid on top of the image using the specified colors. The resulting plot can be used to visualize the location of structures or regions of interest in the image.


.. code-block:: python

    import medviz

    medviz.gif(
        image_path="dataset/1-1.nii",
        mask_paths=[
            "dataset/small_bowel.nii",
            "dataset/1-1-label.nii",
            "dataset/vertebrae_L3.nii.gz",
            "dataset/vertebrae_L4.nii.gz",
            "dataset/vertebrae_L5.nii.gz",
        ],
        mask_colors=["red", "yellow", "green", "blue", "purple"],
        title="Expert Annotations",
        interval=70,
        start_slice=30,
        end_slice=130,
        save_path="animation.gif",
    )

The `gif` function creates an animated GIF of an image and one or more masks. The masks are overlaid on top of the image using the specified colors. The resulting GIF can be used to visualize the location of structures or regions of interest in the image.

GitHub repository: https://github.com/mohsenhariri/kvq

            

Raw data

            {
    "_id": null,
    "home_page": null,
    "name": "kvquant",
    "maintainer": null,
    "docs_url": null,
    "requires_python": ">=3.10",
    "maintainer_email": null,
    "keywords": "Large Language Models, Cache, Quantization, Compression, Optimization",
    "author": null,
    "author_email": "Mohsen Hariri <mohsen.hariri@case.edu>",
    "download_url": "https://files.pythonhosted.org/packages/2e/5e/ffe798a412d038c5a6b045f247aac5dd6859eeac034cfbe1548a640927c4/kvquant-0.0.1.tar.gz",
    "platform": null,
    "description": "==============\nkvq\n==============\n\nMore for Keys, Less for Values: Adaptive KV Cache Quantization \u261d\ufe0f\ud83d\udd11\ud83d\udc47\ud83d\udd22\n\n\nInstallation\n------------\n\nTo install the package, use pip:\n\n.. code-block:: bash\n\n    pip install kvq\n\n\nUsage\n-----\n\nTo use the package, import it in your Python code:\n\n.. code-block:: python\n\n    import kvq\n\n    medviz.layered_plot(image_path=\"dataset/1-1.nii\", mask_paths=[\"dataset/small_bowel.nii\", \"dataset/1-1-label.nii\"], mask_colors=[\"red\", \"yellow\"], title=\"Layered Plot\")\n\nThe `layered_plot` function creates a layered plot of an image and one or more masks. The masks are overlaid on top of the image using the specified colors. The resulting plot can be used to visualize the location of structures or regions of interest in the image.\n\n\n.. code-block:: python\n\n    import medviz\n\n    medviz.gif(\n        image_path=\"dataset/1-1.nii\",\n        mask_paths=[\n            \"dataset/small_bowel.nii\",\n            \"dataset/1-1-label.nii\",\n            \"dataset/vertebrae_L3.nii.gz\",\n            \"dataset/vertebrae_L4.nii.gz\",\n            \"dataset/vertebrae_L5.nii.gz\",\n        ],\n        mask_colors=[\"red\", \"yellow\", \"green\", \"blue\", \"purple\"],\n        title=\"Expert Annotations\",\n        interval=70,\n        start_slice=30,\n        end_slice=130,\n        save_path=\"animation.gif\",\n    )\n\nThe `gif` function creates an animated GIF of an image and one or more masks. The masks are overlaid on top of the image using the specified colors. The resulting GIF can be used to visualize the location of structures or regions of interest in the image.\n\nGitHub repository: https://github.com/mohsenhariri/kvq\n",
    "bugtrack_url": null,
    "license": "GPL-3.0 License",
    "summary": "More for Keys, Less for Values: Adaptive KV Cache Quantization \ud83d\udc0d\ud83d\ude80\ud83c\udf89\ud83e\udd95",
    "version": "0.0.1",
    "project_urls": null,
    "split_keywords": [
        "large language models",
        " cache",
        " quantization",
        " compression",
        " optimization"
    ],
    "urls": [
        {
            "comment_text": null,
            "digests": {
                "blake2b_256": "2cc527df01902936588c338f373d0ba765207efc6fef6e3542fb2e9902fad4b3",
                "md5": "db319d617ca720a32f0c6615dd5b23bc",
                "sha256": "0407337ca40b1bb519c54d35426dbb764faf583fa8bea711cbfa060bc8a30c82"
            },
            "downloads": -1,
            "filename": "kvquant-0.0.1-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "db319d617ca720a32f0c6615dd5b23bc",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.10",
            "size": 14336,
            "upload_time": "2025-02-27T20:12:36",
            "upload_time_iso_8601": "2025-02-27T20:12:36.598392Z",
            "url": "https://files.pythonhosted.org/packages/2c/c5/27df01902936588c338f373d0ba765207efc6fef6e3542fb2e9902fad4b3/kvquant-0.0.1-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": null,
            "digests": {
                "blake2b_256": "2e5effe798a412d038c5a6b045f247aac5dd6859eeac034cfbe1548a640927c4",
                "md5": "e4f620dc278018914fcf223a368f8457",
                "sha256": "0212cf16559775a3ead1bbd17291537827d3fa1a12fc7a74f040d8168788c8d9"
            },
            "downloads": -1,
            "filename": "kvquant-0.0.1.tar.gz",
            "has_sig": false,
            "md5_digest": "e4f620dc278018914fcf223a368f8457",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.10",
            "size": 14980,
            "upload_time": "2025-02-27T20:12:37",
            "upload_time_iso_8601": "2025-02-27T20:12:37.709537Z",
            "url": "https://files.pythonhosted.org/packages/2e/5e/ffe798a412d038c5a6b045f247aac5dd6859eeac034cfbe1548a640927c4/kvquant-0.0.1.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2025-02-27 20:12:37",
    "github": false,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "lcname": "kvquant"
}
        
Elapsed time: 1.58066s