A Rust, Python and gRPC server for text generation inference. Used in production at [HuggingFace](https://huggingface.co)
to power LLMs api-inference widgets.
## Table of contents
- [Features](#features)
- [Optimized Architectures](#optimized-architectures)
- [Get Started](#get-started)
- [Docker](#docker)
- [API Documentation](#api-documentation)
- [A note on Shared Memory](#a-note-on-shared-memory-shm)
- [Distributed Tracing](#distributed-tracing)
- [Local Install](#local-install)
- [CUDA Kernels](#cuda-kernels)
- [Run BLOOM](#run-bloom)
- [Download](#download)
- [Run](#run)
- [Quantization](#quantization)
- [Develop](#develop)
- [Testing](#testing)
## Features
- Serve the most popular Large Language Models with a simple launcher
- Tensor Parallelism for faster inference on multiple GPUs
- Token streaming using Server-Sent Events (SSE)
- [Continuous batching of incoming requests](https://github.com/huggingface/text-generation-inference/tree/main/router) for increased total throughput
- Optimized transformers code for inference using [flash-attention](https://github.com/HazyResearch/flash-attention) and [Paged Attention](https://github.com/vllm-project/vllm) on the most popular architectures
- Quantization with [bitsandbytes](https://github.com/TimDettmers/bitsandbytes) and [GPT-Q](https://arxiv.org/abs/2210.17323)
- [Safetensors](https://github.com/huggingface/safetensors) weight loading
- Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226)
- Logits warper (temperature scaling, top-p, top-k, repetition penalty, more details see [transformers.LogitsProcessor](https://huggingface.co/docs/transformers/internal/generation_utils#transformers.LogitsProcessor))
- Stop sequences
- Log probabilities
- Production ready (distributed tracing with Open Telemetry, Prometheus metrics)
## Optimized architectures
- [BLOOM](https://huggingface.co/bigscience/bloom)
- [FLAN-T5](https://huggingface.co/google/flan-t5-xxl)
- [Galactica](https://huggingface.co/facebook/galactica-120b)
- [GPT-Neox](https://huggingface.co/EleutherAI/gpt-neox-20b)
- [Llama](https://github.com/facebookresearch/llama)
- [OPT](https://huggingface.co/facebook/opt-66b)
- [SantaCoder](https://huggingface.co/bigcode/santacoder)
- [Starcoder](https://huggingface.co/bigcode/starcoder)
- [Falcon 7B](https://huggingface.co/tiiuae/falcon-7b)
- [Falcon 40B](https://huggingface.co/tiiuae/falcon-40b)
- [MPT](https://huggingface.co/mosaicml/mpt-30b)
- [Llama V2](https://huggingface.co/meta-llama)
Other architectures are supported on a best effort basis using:
`AutoModelForCausalLM.from_pretrained(