neuralmagic Goto Github PK

alpaca_eval

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

aws-do-eks

band_of_the_hawk

Hackathon 2022

clip_benchmark

CLIP-like model evaluation

compressed-tensors

TODO: Finalize name

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

deepsparse

Sparsity-aware deep learning inference runtime for CPUs

deepsparse-digitalocean-image

Repo for building and packaging a 1-click app for DigitalOcean

docs

Top-level directory for documentation and general content

examples

Notebooks using the Neural Magic libraries 📓

hackathon_2024

woop wooop

inference

Reference implementations of MLPerf™ inference benchmarks

langchain

⚡ Building applications with LLMs through composability ⚡

lm-evaluation-harness

A framework for few-shot evaluation of autoregressive language models.

mlperf_inference_results_v2.1

mlperf_inference_results_v3.0

nm-actions

Neural Magic GHA

nm-autogptq

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

nm-docker

Neural Magic Docker

nm-vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

optimum-deepsparse

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

sahi

Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

sparseml

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

sparsezoo

Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes

sparsify

ML model optimization product to accelerate inference.

to-be-removed-llm-foundry

LLM training code for MosaicML foundation models

transformers

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

upstream-composer

Supercharge Your Model Training

upstream-llm-foundry

LLM training code for MosaicML foundation models