An open API service providing package, version and dependency metadata of many open source software ecosystems and registries.

proxy.golang.org "quantization" keyword

View the packages on the proxy.golang.org package registry that are tagged with the "quantization" keyword.

Top 9.6% on proxy.golang.org
github.com/google/qkeras v0.9.0
QKeras: a quantization deep learning library for Tensorflow Keras
6 versions - Latest release: almost 5 years ago - 514 stars on GitHub
Top 5.6% on proxy.golang.org
github.com/intel/auto-round v0.10.0
Advanced Quantization Algorithm for LLMs and VLMs, with support for CPU, Intel GPU, CUDA and HPU.
24 versions - Latest release: about 16 hours ago - 668 stars on GitHub
Top 5.8% on proxy.golang.org
github.com/Smallsan/octreequant
Oct tree color quantization algorithm
Latest release: 2 months ago - 0 stars on GitHub
Top 6.7% on proxy.golang.org
github.com/hiyouga/llama-factory v0.9.4
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
35 versions - Latest release: about 1 month ago - 60,871 stars on GitHub
Top 6.7% on proxy.golang.org
github.com/intel/neural-compressor v3.7.1+incompatible
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techn...
22 versions - Latest release: 29 days ago - 2,512 stars on GitHub
Top 6.6% on proxy.golang.org
github.com/NervanaSystems/distiller v0.3.2
Neural Network Distiller by Intel AI Lab: a Python package for neural network compression researc...
6 versions - Latest release: over 6 years ago - 4,310 stars on GitHub
Top 6.7% on proxy.golang.org
github.com/pytorch/ao v0.15.0
PyTorch native quantization and sparsity for training and inference
63 versions - Latest release: about 2 months ago - 2,464 stars on GitHub
Top 6.6% on proxy.golang.org
github.com/mobiusml/hqq v0.2.8
Official implementation of Half-Quadratic Quantization (HQQ)
3 versions - Latest release: 6 months ago - 881 stars on GitHub
Top 5.5% on proxy.golang.org
github.com/mit-han-lab/nunchaku v1.2.1
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
14 versions - Latest release: 19 days ago - 1,975 stars on GitHub
Top 5.6% on proxy.golang.org
github.com/huggingface/optimum-quanto v0.2.7
A pytorch quantization backend for optimum
11 versions - Latest release: 11 months ago - 994 stars on GitHub
Top 8.2% on proxy.golang.org
github.com/nazarhussain/camalian v0.2.2
Library used to deal with colors and images. You can extract colors from images.
5 versions - Latest release: almost 5 years ago - 48 stars on GitHub
Top 5.6% on proxy.golang.org
github.com/autogptq/autogptq v0.7.1
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
18 versions - Latest release: almost 2 years ago - 4,989 stars on GitHub
Top 5.6% on proxy.golang.org
github.com/openvinotoolkit/training_extensions v1.0.1
Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™
12 versions - Latest release: almost 3 years ago - 1,189 stars on GitHub
Top 6.7% on proxy.golang.org
github.com/neuralmagic/deepsparse v1.9.0
Sparsity-aware deep learning inference runtime for CPUs
42 versions - Latest release: 9 months ago - 3,158 stars on GitHub
Top 6.7% on proxy.golang.org
github.com/tensorflow/model-optimization v0.8.0
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization a...
22 versions - Latest release: about 2 years ago - 1,557 stars on GitHub
Top 6.7% on proxy.golang.org
github.com/stochasticai/xturing v0.1.8
Build, personalize and control your own LLMs. From data pre-processing to fine-tuning, xTuring pr...
9 versions - Latest release: over 2 years ago - 2,665 stars on GitHub
Top 5.6% on proxy.golang.org
github.com/AutoGPTQ/AutoGPTQ v0.7.1
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
18 versions - Latest release: almost 2 years ago - 4,985 stars on GitHub
Top 5.6% on proxy.golang.org
github.com/thu-ml/sageattention v2.2.0+incompatible
Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, w...
2 versions - Latest release: 4 months ago - 2,418 stars on GitHub
Top 5.6% on proxy.golang.org
github.com/thu-ml/SageAttention v2.2.0+incompatible
Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, w...
2 versions - Latest release: 4 months ago - 2,418 stars on GitHub
Top 5.3% on proxy.golang.org
github.com/wizenheimer/comet v0.1.1
Package comet implements a BM25-based full-text search index. WHAT IS BM25? BM25 (Best Matching ...
2 versions - Latest release: 4 months ago - 32 stars on GitHub
Top 5.6% on proxy.golang.org
github.com/NervanaSystems/nlp-architect v0.5.5
A model library for exploring state-of-the-art deep learning topologies and techniques for optimi...
6 versions - Latest release: over 5 years ago - 2,940 stars on GitHub
Top 6.7% on proxy.golang.org
github.com/panqiwei/autogptq v0.7.1
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
18 versions - Latest release: almost 2 years ago - 3,896 stars on GitHub
Top 6.7% on proxy.golang.org
github.com/OpenNMT/CTranslate2 v4.6.3+incompatible
Fast inference engine for Transformer models
159 versions - Latest release: about 1 month ago - 4,048 stars on GitHub
Top 8.2% on proxy.golang.org
github.com/georgy7/toyfloat v1.11.0
Package toyfloat provides tiny (3 to 16 bits) floating-point number formats for serialization.
24 versions - Latest release: almost 4 years ago - 0 stars on GitHub
Top 5.7% on proxy.golang.org
github.com/OpenGVLab/OmniQuant v0.0.1
[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.
1 version - Latest release: over 2 years ago - 805 stars on GitHub
Top 5.6% on proxy.golang.org
github.com/nervanasystems/nlp-architect v0.5.5
A model library for exploring state-of-the-art deep learning topologies and techniques for optimi...
6 versions - Latest release: over 5 years ago - 2,940 stars on GitHub
Top 8.2% on proxy.golang.org
github.com/xilinx/finn v0.10.1
Dataflow compiler for QNN inference on FPGAs
2 versions - Latest release: over 1 year ago - 891 stars on GitHub
Top 6.7% on proxy.golang.org
github.com/opengvlab/omniquant v0.0.1
[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.
1 version - Latest release: over 2 years ago - 546 stars on GitHub
Top 6.7% on proxy.golang.org
github.com/guillaumekln/faster-whisper v1.2.1
Faster Whisper transcription with CTranslate2
21 versions - Latest release: 3 months ago - 9,301 stars on GitHub
Top 6.7% on proxy.golang.org
github.com/hiyouga/LLaMA-Factory v0.9.4
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
35 versions - Latest release: about 1 month ago - 60,871 stars on GitHub
Top 8.2% on proxy.golang.org
github.com/Xilinx/finn v0.10.1
Dataflow compiler for QNN inference on FPGAs
2 versions - Latest release: over 1 year ago - 891 stars on GitHub
Top 10.0% on proxy.golang.org
github.com/joshdk/quantize v0.0.0-20171110221748-65999d3a4c76
🎨 Simple color palette quantization using MMCQ
1 version - Latest release: over 8 years ago - 1 dependent repositories - 30 stars on GitHub
Top 4.9% on proxy.golang.org
github.com/intel/intel-extension-for-pytorch v1.12.300
A Python package for extending the official PyTorch that can easily obtain performance on Intel p...
14 versions - Latest release: over 3 years ago - 1,977 stars on GitHub
Top 6.6% on proxy.golang.org
github.com/nervanasystems/distiller v0.3.2
Neural Network Distiller by Intel AI Lab: a Python package for neural network compression researc...
6 versions - Latest release: over 6 years ago - 4,310 stars on GitHub
Top 5.6% on proxy.golang.org
github.com/hiyouga/LLaMA-Efficient-Tuning v0.9.3
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
34 versions - Latest release: 8 months ago - 50,686 stars on GitHub
Top 5.6% on proxy.golang.org
github.com/hiyouga/llama-efficient-tuning v0.9.3
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
34 versions - Latest release: 8 months ago - 50,686 stars on GitHub
Top 6.7% on proxy.golang.org
github.com/SYSTRAN/faster-whisper v1.2.1
Faster Whisper transcription with CTranslate2
21 versions - Latest release: 3 months ago - 18,751 stars on GitHub
Top 5.7% on proxy.golang.org
github.com/huggingface/optimum v2.1.0+incompatible
🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers ...
82 versions - Latest release: about 2 months ago - 3,121 stars on GitHub
Top 6.7% on proxy.golang.org
github.com/systran/faster-whisper v1.2.1
Faster Whisper transcription with CTranslate2
21 versions - Latest release: 3 months ago - 18,751 stars on GitHub
Top 5.7% on proxy.golang.org
github.com/inisis/brocolli v4.0.2+incompatible
Everything in Torch Fx
2 versions - Latest release: over 2 years ago - 344 stars on GitHub
Top 9.6% on proxy.golang.org
github.com/retraigo/monke v1.0.2 💰
Color quantization and dithering in TypeScript.
8 versions - Latest release: over 2 years ago - 6 stars on GitHub
Top 6.7% on proxy.golang.org
github.com/open-mmlab/mmrazor v1.0.0
OpenMMLab Model Compression Toolbox and Benchmark.
5 versions - Latest release: almost 3 years ago - 1,627 stars on GitHub
Top 6.7% on proxy.golang.org
github.com/PanQiWei/AutoGPTQ v0.7.1
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
18 versions - Latest release: almost 2 years ago - 3,896 stars on GitHub
Top 5.6% on proxy.golang.org
github.com/openvinotoolkit/nncf v2.19.0+incompatible
Neural Network Compression Framework for enhanced OpenVINO™ inference
31 versions - Latest release: 2 months ago - 1,089 stars on GitHub
Top 6.5% on proxy.golang.org
github.com/ModelTC/llmc v1.5.0
llmc is an efficient LLM compression tool with various advanced compression methods, supporting m...
4 versions - Latest release: 3 months ago - 25 stars on GitHub
Top 4.6% on proxy.golang.org
github.com/esimov/colorquant v1.0.0
Go library for color quantization and dithering
1 version - Latest release: over 8 years ago - 6 dependent packages - 6 dependent repositories - 81 stars on GitHub
Top 6.5% on proxy.golang.org
github.com/modeltc/llmc v1.5.0
llmc is an efficient LLM compression tool with various advanced compression methods, supporting m...
4 versions - Latest release: 3 months ago - 25 stars on GitHub
Top 6.7% on proxy.golang.org
github.com/opennmt/ctranslate2 v4.6.2+incompatible
Fast inference engine for Transformer models
158 versions - Latest release: 2 months ago - 4,048 stars on GitHub