{"domain":"inferenceengineering.tech","status":"valid","tier":"listed","authority":46,"verified":false,"title":"Inference Engineering","summary":"The definitive interactive guide to AI model inference — GPU hardware, inference engines (vLLM, SGLang, TensorRT-LLM), quantization, KV caching, and production autoscaling. Written by Philip Kiely, published by Baseten Books.","country":"US","country_source":"ip","publisher_country":null,"publisher_country_source":null,"hosting_country":"US","llms_txt":"https://inferenceengineering.tech/llms.txt","llms_full_txt":"https://inferenceengineering.tech/llms-full.txt","last_checked":"2026-10-27T13:35:21.698Z","agent_terms":null,"categories":["ai-ml","documentation-reference"],"capabilities":[],"inferred_tags":["ai-inference","gpu-hardware","vllm","quantization","kv-caching"],"audience":"developers","agent_uses":["read_docs"],"language":"en","platform_generated":false,"agent_summary":"Interactive book-style guide to AI model inference covering GPU hardware, vLLM, SGLang, TensorRT-LLM, quantization, KV caching and autoscaling, with benchmarks ","llms_txt_cached":"https://agentwebmap.com/v1/domain/inferenceengineering.tech/llms.txt","agentic":"documentation","section_keys":["about","chapters","interactive-tools","key-resources","learn-articles","note"],"section_partial":false,"section_indexed_at":"2026-10-27T13:35:51.312Z"}