HighSpeeds

HighSpeeds's Stars

• facebookresearch/faiss

  A library for efficient similarity search and clustering of dense vectors.

  Language:C++34k4812.6k3.8k

• microsoft/LoRA

  Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

  Language:Python11.6k69114730

• mistralai/mistral-inference

  Official inference library for Mistral models

  Language:Jupyter Notebook10.1k129150908

• EleutherAI/lm-evaluation-harness

  A framework for few-shot evaluation of language models.

  Language:Python8.4k391.3k2.3k

• quic/aimet

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

  Language:Python2.3k491.4k398

• cvxgrp/cvxpylayers

  Differentiable convex optimization layers

  Language:Python1.9k57116169

• kyegomez/BitNet

  Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

  Language:Python1.8k4344160

• Vahe1994/AQLM

  Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf and PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression https://arxiv.org/abs/2405.14852

  Language:Python1.2k18106182

• acl-org/acl-style-files

  Official style files for papers submitted to venues of the Association for Computational Linguistics

  Language:TeX996833216

• OpenGVLab/OmniQuant

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

  Language:Python789178860

• IST-DASLab/sparsegpt

  Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".

  Language:Python7761533102

• locuslab/wanda

  A simple and effective LLM pruning approach.

  Language:Python727869101

• siboehm/SGEMM_CUDA

  Fast CUDA matrix multiplication from scratch

  Language:Cuda66841693

• microsoft/VPTQ

  VPTQ, A Flexible and Extreme low-bit quantization algorithm

  Language:Cuda620185642

• cvxgrp/scs

  Splitting Conic Solver

  Language:C56834185138

• Zhen-Dong/Awesome-Quantization-Papers

  List of papers related to neural network quantization in recent AI conferences and journals.

  56416247

• Cornell-RelaxML/quip-sharp

  Language:Python529136845

• subhadarship/kmeans_pytorch

  kmeans using PyTorch

  Language:Jupyter Notebook50983782

• facebookresearch/dietgpu

  GPU implementation of a fast generalized ANS (asymmetric numeral system) entropy encoder and decoder, with extensions for lossless compression of numerical and other data types in HPC/ML applications.

  Language:Cuda32218528

• yhhhli/APoT_Quantization

  PyTorch implementation for the APoT quantization (ICLR 2020)

  Language:Python27142651

• patrick-kidger/torchcubicspline

  Interpolating natural cubic splines. Includes batching, GPU support, support for missing values, evaluating derivatives of the spline, and backpropagation.

  Language:Python24531321

• yxli2123/LoftQ

  Language:Python22043820

• uanu2002/JSQ

  [ICML 2024] JSQ: Compressing Large Language Models by Joint Sparsification and Quantization

  Language:Python148645

• Cornell-RelaxML/qtip

  Language:Python112111513

• yxli2123/LoSparse

  Language:Python50166

• csyhhu/L-DNQ

  Codes for AAAI2019 paper: Deep Neural Network Quantization via Layer-Wise Optimization using Limited Training Data

  Language:Python41408

• quanta-fine-tuning/quanta

  (NeurIPS 2024) QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation

  Language:Python23014

• kssteven418/SqueezeLLM-gradients

  Language:Python18247

• roychowdhuryresearch/pyHFO

  STE/MNI HFO detection, classification and visualization

  Language:Python8431

• lihuang258/LoRAP

  [ICML 2024]: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models

  Language:Python5