accelerated-pytorch-transformers-generation

starcoder

Home of StarCoder: fine-tuning & inference!

BertSum

Code for paper Fine-tune BERT for Extractive Summarization

GPTQ-for-LLaMa

4 bits quantization of LLaMA using GPTQ

FlexiGen

Running large language models on a single GPU for throughput-oriented scenarios.

maxtext

A simple, performant and scalable Jax LLM!

diffusers-torchao

End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 ...

SpQR

llm-inference-benchmark

LLM Inference benchmark

minimal-gpt-neox-20b

minimal-llama

starcoder2

Home of StarCoder2!

llmsearch

Find better generation parameters for your LLM

Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

torchprep