Text Generation Inference

Text Generation Inference (TGI) is a toolkit for deploying and serving Large Language Models (LLMs). TGI enables high-performance text generation for the most popular open-source LLMs, including Llama, Falcon, StarCoder, BLOOM, GPT-NeoX, and T5.

Text Generation Inference implements many optimizations and features, such as:

• Simple launcher to serve most popular LLMs
• Production ready (distributed tracing with Open Telemetry, Prometheus metrics)
• Tensor Parallelism for faster inference on multiple GPUs
• Token streaming using Server-Sent Events (SSE)
• Continuous batching of incoming requests for increased total throughput
• Optimized transformers code for inference using Flash Attention and Paged Attention on the most popular architectures
• Quantization with bitsandbytes and GPT-Q
• Safetensors weight loading
• Watermarking with A Watermark for Large Language Models
• Logits warper (temperature scaling, top-p, top-k, repetition penalty)
• Stop sequences
• Log probabilities

Text Generation Inference is used in production by multiple projects, such as:

• Hugging Chat, an open-source interface for open-access models, such as Open Assistant and Llama
• OpenAssistant, an open-source community effort to train LLMs in the open
• nat.dev, a playground to explore and compare LLMs.