#Quantization

Showing 60 of 101 repositories tagged #quantization, ranked by stars

hiyouga
hiyouga
LlamaFactory

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Score
100
★ 73.1k ⑂ 8.9k +120/day
Python
SYSTRAN
SYSTRAN
faster-whisper

Faster Whisper transcription with CTranslate2

Score
62
★ 24.1k ⑂ 2.0k +78/day
Python
ymcui
ymcui
Chinese-LLaMA-Alpaca

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

Score
88
★ 18.9k ⑂ 1.9k +2/day
Python
UFund-Me
UFund-Me
Qbot

[🔥updating ...] AI 自动量化交易机器人(完全本地部署) AI-powered Quantitative Investment Research Platform. 📃 online docs: https://ufund-me.github.io/Qbot ✨ :news: qbot-mini: https://github.com/Charmve/iQuant

Score
0
★ 18.0k ⑂ 2.5k +72/day
Jupyter Notebook
RyanCodrai
RyanCodrai
turbovec

A vector index built on TurboQuant, written in Rust with Python bindings

Score
75
★ 12.6k ⑂ 1.1k +59/day
Python
bitsandbytes-foundation
bitsandbytes-foundation
bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

Score
50
★ 8.3k ⑂ 882 +1/day
Python
AutoGPTQ
AutoGPTQ
AutoGPTQ

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

Score
75
★ 5.1k ⑂ 540
Python
OpenNMT
OpenNMT
CTranslate2

Fast inference engine for Transformer models

Score
100
★ 4.6k ⑂ 496 +3/day
C++
thu-ml
thu-ml
SageAttention

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

Score
98
★ 3.5k ⑂ 441 +12/day
Cuda
neuralmagic
neuralmagic
deepsparse

Sparsity-aware deep learning inference runtime for CPUs

Score
64
★ 3.2k ⑂ 191
Python
IntelLabs
IntelLabs
nlp-architect

A model library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing neural networks

Score
67
★ 2.9k ⑂ 441
Python
stochasticai
stochasticai
xTuring

Build, personalize and control your own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6

Score
95
★ 2.7k ⑂ 210 +3/day
Python
qualcomm
qualcomm
aimet

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

Score
97
★ 2.7k ⑂ 459
Python
Efficient-ML
Efficient-ML
Awesome-Model-Quantization

A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (papers, repositories) that are missed by the repo.

Score
94
★ 2.4k ⑂ 240 +1/day
adithya-s-k
adithya-s-k
AI-Engineering.academy

Mastering Applied AI, One Concept at a Time

Score
93
★ 2.3k ⑂ 270 +111/day
Jupyter Notebook
dvmazur
dvmazur
mixtral-offloading

Run Mixtral-8x7B models in Colab or consumer desktops

Score
65
★ 2.3k ⑂ 227
Python
amitshekhariitbhu
amitshekhariitbhu
ai-engineering-interview-questions

Your Cheat Sheet for AI Engineering Interview – Questions and Answers.

Score
100
★ 2.1k ⑂ 384 +36/day
Markdown
intel
intel
intel-extension-for-pytorch

A Python package for extending the official PyTorch that can easily obtain performance on Intel platform

Score
83
★ 2.0k ⑂ 319
Python
OpenPPL
OpenPPL
ppq

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

Score
53
★ 1.8k ⑂ 283 +1/day
Python
RightNow-AI
RightNow-AI
picolm

Run a 1-billion parameter LLM on a $10 board with 256MB RAM

Score
86
★ 1.7k ⑂ 220 +1/day
C
RWKV
RWKV
rwkv.cpp

INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model

Score
56
★ 1.6k ⑂ 128
C++
tensorflow
tensorflow
model-optimization

A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.

Score
92
★ 1.6k ⑂ 348
Python
Xilinx
Xilinx
brevitas

Brevitas: neural network quantization in PyTorch

Score
86
★ 1.5k ⑂ 245 +3/day
Python
intel
intel
auto-round

A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.

Score
38
★ 1.5k ⑂ 150 +6/day
Python
RahulSChand
RahulSChand
gpu_poor

Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization

Score
53
★ 1.4k ⑂ 89 +1/day
JavaScript
Tencent
Tencent
AngelSlim

Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.

Score
88
★ 1.4k ⑂ 156 +29/day
Python
open-edge-platform
open-edge-platform
geti

Build computer vision models in a fraction of the time and with less data.

Score
89
★ 1.3k ⑂ 471
Python
openvinotoolkit
openvinotoolkit
nncf

Neural Network Compression Framework for enhanced OpenVINO™ inference

Score
91
★ 1.2k ⑂ 299
Python
IST-DASLab
IST-DASLab
marlin

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

Score
47
★ 1.1k ⑂ 90 +3/day
Python
Xilinx
Xilinx
finn

Dataflow compiler for QNN inference on FPGAs

Score
81
★ 1.0k ⑂ 301 +2/day
Python
thu-ml
thu-ml
SpargeAttn

[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

Score
84
★ 1.0k ⑂ 95 +3/day
Cuda
PINTO0309
PINTO0309
onnx2tf

A tool for converting ONNX files to LiteRT/TFLite/TensorFlow, PyTorch native code (nn.Module), TorchScript (.pt), state_dict (.pt), Exported Program (.pt2), and Dynamo ONNX. It also supports direct conversion from LiteRT to PyTorch.

Score
25
★ 972 ⑂ 105 +1/day
Python
mit-han-lab
mit-han-lab
TinyChatEngine

TinyChatEngine: On-Device LLM Inference Library

Score
44
★ 956 ⑂ 100
C++
mit-han-lab
mit-han-lab
tinyengine

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory

Score
47
★ 951 ⑂ 161
C
dropbox
dropbox
hqq

Official implementation of Half-Quadratic Quantization (HQQ)

Score
12
★ 947 ⑂ 90
Python
ImageOptim
ImageOptim
libimagequant

Palette quantization library that powers pngquant and other PNG optimizers

Score
100
★ 921 ⑂ 141 +1/day
Rust
OpenGVLab
OpenGVLab
OmniQuant

[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.

Score
72
★ 900 ⑂ 83
Python
csarron
csarron
awesome-emdl

Embedded and mobile deep learning research resources

Score
42
★ 769 ⑂ 168
ModelTC
ModelTC
LightCompress

[EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.

Score
81
★ 731 ⑂ 78
Python
SqueezeAILab
SqueezeAILab
SqueezeLLM

[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

Score
40
★ 722 ⑂ 51
Python
hailo-ai
hailo-ai
hailo_model_zoo

The Hailo Model Zoo includes pre-trained models and a full building and evaluation environment

Score
78
★ 673 ⑂ 85
Python
SforAiDl
SforAiDl
KD_Lib

A Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.

Score
100
★ 650 ⑂ 61 +1/day
Python
Ki6an
Ki6an
fastT5

⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.

Score
33
★ 588 ⑂ 75
Python
google
google
qkeras

QKeras: a quantization deep learning library for Tensorflow Keras

Score
72
★ 584 ⑂ 108 +1/day
Python
slavabarkov
slavabarkov
tidy

Offline semantic Text-to-Image and Image-to-Image search on Android powered by quantized state-of-the-art vision-language pretrained CLIP model and ONNX Runtime inference engine

Score
0
★ 576 ⑂ 43
Kotlin
Maknee
Maknee
minigpt4.cpp

Port of MiniGPT4 in C++ (4bit, 5bit, 6bit, 8bit, 16bit CPU inference with GGML)

Score
28
★ 573 ⑂ 28
C++
thulab
thulab
DeepHash

An Open-Source Package for Deep Learning to Hash (DeepHash)

Score
36
★ 563 ⑂ 124
Python
cedrickchee
cedrickchee
awesome-ml-model-compression

Awesome machine learning model compression research papers, quantization, tools, and learning material.

Score
31
★ 546 ⑂ 62
zengxiao-he
zengxiao-he
tessera

From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracle, and interpretability tooling.

Score
50
★ 512 ⑂ 5 +24/day
Python
Kaden-Schutt
Kaden-Schutt
hipfire

RDNA-native LLM inference engine in Rust.

Score
75
★ 467 ⑂ 50 +3/day
Rust
1duo
1duo
awesome-ai-infrastructures

Infrastructures™ for Machine Learning Training/Inference in Production.

Score
0
★ 454 ⑂ 88
SonySemiconductorSolutions
SonySemiconductorSolutions
mct-model-optimization

Model Compression Toolkit (MCT) is an open source project for neural network model optimization under efficient, constrained hardware. This project provides researchers, developers, and engineers advanced quantization and compression tools for deploying state-of-the-art neural networks.

Score
69
★ 448 ⑂ 80
Python
huawei-csl
huawei-csl
KVarN

KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.

Score
77
★ 434 ⑂ 28 +4/day
Python
SqueezeAILab
SqueezeAILab
KVQuant

[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Score
33
★ 430 ⑂ 46
Python
jy-yuan
jy-yuan
KIVI

[ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Score
58
★ 414 ⑂ 55 +1/day
Python
datawhalechina
datawhalechina
llm-deploy

大模型/LLM推理和部署理论与实践

Score
30
★ 407 ⑂ 52 +1/day
AEON-7
AEON-7
Qwen3.6-27B-AEON-Ultimate-Uncensored-DFlash

Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.io/aeon-7/aeon-vllm-ultimate:latest container, tuned for long-context draft acceptance on DGX Spark. 6 HF variants (BF16/NVFP4/MTP/MTP-XS), docker-compose, and QuickStart.

Score
79
★ 403 ⑂ 41 +3/day
Python
FujitsuResearch
FujitsuResearch
OneCompression

Python package for LLM compression

Score
74
★ 396 ⑂ 18 +2/day
Python
quantumaikr
quantumaikr
quant.cpp

LLM inference with 7x longer context. Pure C, zero dependencies. Lossless KV cache compression + single-header library.

Score
70
★ 395 ⑂ 43
C
sinanuozdemir
sinanuozdemir
quick-start-guide-to-llms

The Official Repo for "Quick Start Guide to Large Language Models"

Score
60
★ 392 ⑂ 213
Jupyter Notebook
Related Topics
#llm#deep-learning#machine-learning#pytorch#large-language-models#pruning#nlp#inference#transformer#llama#model-compression#transformers

© 2026 GitRepoTrend · GitHub repositories by topic · Updated weekly