RezaYazdaniAminabadi

bigcode-evaluation-harness

A framework for the evaluation of autoregressive code generation language models.

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

DS-Kernels

FlashAttention

Fast and memory-efficient exact attention

llama

Inference code for LLaMA models

llama2.c

Inference Llama 2 in one file of pure C

lm-evaluation-harness

A framework for few-shot evaluation of language models.

transformers

transformers-1

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

transformers-bloom-inference

Fast Inference Solutions for BLOOM

triton

Development repository for the Triton language and compiler

vllm

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