77 lines
2.3 KiB
YAML
77 lines
2.3 KiB
YAML
- sections:
|
|
- local: index
|
|
title: Text Generation Inference
|
|
- local: quicktour
|
|
title: Quick Tour
|
|
- local: installation_nvidia
|
|
title: Using TGI with Nvidia GPUs
|
|
- local: installation_amd
|
|
title: Using TGI with AMD GPUs
|
|
- local: installation_gaudi
|
|
title: Using TGI with Intel Gaudi
|
|
- local: installation_inferentia
|
|
title: Using TGI with AWS Inferentia
|
|
- local: installation_intel
|
|
title: Using TGI with Intel GPUs
|
|
- local: installation
|
|
title: Installation from source
|
|
- local: supported_models
|
|
title: Supported Models and Hardware
|
|
- local: architecture
|
|
title: Internal Architecture
|
|
- local: usage_statistics
|
|
title: Usage Statistics
|
|
title: Getting started
|
|
- sections:
|
|
- local: basic_tutorials/consuming_tgi
|
|
title: Consuming TGI
|
|
- local: basic_tutorials/preparing_model
|
|
title: Preparing Model for Serving
|
|
- local: basic_tutorials/gated_model_access
|
|
title: Serving Private & Gated Models
|
|
- local: basic_tutorials/using_cli
|
|
title: Using TGI CLI
|
|
- local: basic_tutorials/non_core_models
|
|
title: Non-core Model Serving
|
|
- local: basic_tutorials/safety
|
|
title: Safety
|
|
- local: basic_tutorials/using_guidance
|
|
title: Using Guidance, JSON, tools
|
|
- local: basic_tutorials/visual_language_models
|
|
title: Visual Language Models
|
|
- local: basic_tutorials/monitoring
|
|
title: Monitoring TGI with Prometheus and Grafana
|
|
- local: basic_tutorials/train_medusa
|
|
title: Train Medusa
|
|
title: Tutorials
|
|
- sections:
|
|
- local: reference/launcher
|
|
title: All TGI CLI options
|
|
- local: reference/metrics
|
|
title: Exported Metrics
|
|
- local: reference/api_reference
|
|
title: API Reference
|
|
title: Reference
|
|
- sections:
|
|
- local: conceptual/streaming
|
|
title: Streaming
|
|
- local: conceptual/quantization
|
|
title: Quantization
|
|
- local: conceptual/tensor_parallelism
|
|
title: Tensor Parallelism
|
|
- local: conceptual/paged_attention
|
|
title: PagedAttention
|
|
- local: conceptual/safetensors
|
|
title: Safetensors
|
|
- local: conceptual/flash_attention
|
|
title: Flash Attention
|
|
- local: conceptual/speculation
|
|
title: Speculation (Medusa, ngram)
|
|
- local: conceptual/guidance
|
|
title: How Guidance Works (via outlines)
|
|
- local: conceptual/lora
|
|
title: LoRA (Low-Rank Adaptation)
|
|
|
|
|
|
title: Conceptual Guides
|