We identify three pillers to enable fast inference of SoTA AI models on your CPU:
1. Fast C/C++ LLM inference kernels for CPU.
2. Machine Learning Research & Exploration front - Compression through quantization, sparsification, training on more data, collecting data and training instruction & chat models.
3. Easy to use API for fast AI inference in dynamically typed language like Python.
This project aims to address the third using LLaMa.cpp and GGML.
Raw data
{
"_id": null,
"home_page": "",
"name": "cformers",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "python,local inference,c++ inference,language models,cpu inference,quantization",
"author": "Ayush Kaushal (Ayushk4)",
"author_email": "ayush4@utexas.edu",
"download_url": "https://files.pythonhosted.org/packages/9c/27/7505402180b2bd111ce2a3835cd9f2cc9466352c9cfaf5e0d6bd2279a9b6/cformers-0.0.4.tar.gz",
"platform": null,
"description": "We identify three pillers to enable fast inference of SoTA AI models on your CPU:\n1. Fast C/C++ LLM inference kernels for CPU.\n2. Machine Learning Research & Exploration front - Compression through quantization, sparsification, training on more data, collecting data and training instruction & chat models.\n3. Easy to use API for fast AI inference in dynamically typed language like Python.\n\nThis project aims to address the third using LLaMa.cpp and GGML.\n",
"bugtrack_url": null,
"license": "",
"summary": "SoTA Transformers with C-backend for fast inference on your CPU.",
"version": "0.0.4",
"split_keywords": [
"python",
"local inference",
"c++ inference",
"language models",
"cpu inference",
"quantization"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "eee6f9ede7542994a9b94d58a3b0cf106c7ccef788acfe1292b5607ca8e08cfb",
"md5": "ffc7030acdd3afa45a2eac9f68dc3d5f",
"sha256": "f7c769d6a6b39fadcdc1833f5ca89ba005fd999165ab8ad3a8f61a17726902b9"
},
"downloads": -1,
"filename": "cformers-0.0.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "ffc7030acdd3afa45a2eac9f68dc3d5f",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 1041044,
"upload_time": "2023-03-31T07:17:46",
"upload_time_iso_8601": "2023-03-31T07:17:46.765143Z",
"url": "https://files.pythonhosted.org/packages/ee/e6/f9ede7542994a9b94d58a3b0cf106c7ccef788acfe1292b5607ca8e08cfb/cformers-0.0.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "9c277505402180b2bd111ce2a3835cd9f2cc9466352c9cfaf5e0d6bd2279a9b6",
"md5": "b4bea6f5cd76f9d8f12a17338b6ce39b",
"sha256": "ac93556304e4966ed08f0b64fa6a0a01a878eefe9284dd11e47bf16694dc4ba6"
},
"downloads": -1,
"filename": "cformers-0.0.4.tar.gz",
"has_sig": false,
"md5_digest": "b4bea6f5cd76f9d8f12a17338b6ce39b",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 1036750,
"upload_time": "2023-03-31T07:17:53",
"upload_time_iso_8601": "2023-03-31T07:17:53.233565Z",
"url": "https://files.pythonhosted.org/packages/9c/27/7505402180b2bd111ce2a3835cd9f2cc9466352c9cfaf5e0d6bd2279a9b6/cformers-0.0.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-03-31 07:17:53",
"github": false,
"gitlab": false,
"bitbucket": false,
"lcname": "cformers"
}