huggingface / safetensors
Simple, safe way to store and distribute tensors
☆3,221Updated 3 weeks ago
Alternatives and similar repositories for safetensors:
Users that are interested in safetensors are comparing it to the libraries listed below
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆9,319Updated last week
- Accessible large language models via k-bit quantization for PyTorch.☆6,918Updated this week
- 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization…☆2,845Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,002Updated 3 weeks ago
- A machine learning compiler for GPUs, CPUs, and ML accelerators☆3,087Updated this week
- Large Language Model Text Generation Inference☆10,010Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,355Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,922Updated this week
- Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackab…☆1,564Updated last year
- Transformer related optimization, including BERT, GPT☆6,123Updated last year
- Tensor library for machine learning☆12,311Updated this week
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆8,608Updated this week
- Fast and memory-efficient exact attention☆16,835Updated this week
- PyTorch native quantization and sparsity for training and inference☆1,954Updated this week
- Python bindings for the Transformer models implemented in C/C++ using GGML library.☆1,858Updated last year
- A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.☆2,856Updated last year
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,092Updated last week
- Fast inference engine for Transformer models☆3,739Updated last week
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,077Updated last year
- 4 bits quantization of LLaMA using GPTQ☆3,050Updated 9 months ago
- Development repository for the Triton language and compiler☆15,217Updated this week
- SGLang is a fast serving framework for large language models and vision language models.☆13,215Updated this week
- A fast inference library for running LLMs locally on modern consumer-class GPUs☆4,115Updated this week
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,808Updated this week
- Python bindings for llama.cpp☆8,943Updated this week
- TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain…☆10,173Updated this week
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,627Updated 2 weeks ago
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆5,916Updated this week
- PyTorch extensions for high performance and large scale training.☆3,298Updated last week
- Training and serving large-scale neural networks with auto parallelization.☆3,122Updated last year