{"adoption": {"forks": 1280, "observed_at": "2026-08-28T04:10:44.603621+00:00", "stars": 10889}, "canonical_url": "https://ross.abutalabs.com/products/text-generation-inference", "card": {"archived": true, "artifact_type": "service", "description": "Large Language Model Text Generation Inference", "domain": ["large-language-models", "machine-learning", "deep-learning", "self-hosted", "apis"], "enriched": true, "function": ["llm-inference", "http-server", "rpc", "monitoring", "gpu-computing"], "health_score": 10, "homepage": "http://hf.co/docs/text-generation-inference", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["huggingface/text-generation-inference"], "name": "huggingface/text-generation-inference", "platform": ["python", "rust", "self-hosted"], "pushed_at": "2026-03-21T11:34:22+00:00", "repo": "huggingface/text-generation-inference", "stars": 10889, "tags": ["text-generation", "serving", "continuous-batching", "tensor-parallelism", "flash-attention", "paged-attention", "openai-compatible-api", "token-streaming", "huggingface", "docker", "linux", "gpu"], "topics": ["bloom", "nlp", "pytorch", "inference", "gpt", "deep-learning", "transformer", "falcon", "starcoder"], "urls": [], "use_cases": ["serve llama models on a gpu server", "deploy an open-source llm behind an openai-compatible api", "run high-throughput text generation with continuous batching", "host a self-hosted chat completion endpoint", "serve large models across multiple gpus with tensor parallelism", "stream llm tokens over server-sent events"], "what_it_is": "Text Generation Inference (TGI) is a Rust, Python and gRPC toolkit for deploying and serving large language models with high performance, powering Hugging Face's production services. It supports popular open LLMs (Llama, Mistral, Falcon, StarCoder, BLOOM, etc.) with features like continuous batching, tensor parallelism, token streaming, and an OpenAI-compatible Messages API.", "when_to_avoid": ["you want the most actively developed inference engine - TGI is in maintenance mode and recommends vLLM or SGLang", "you need CPU-only or lightweight local inference - llama.cpp or MLX are better fits", "you need to serve model architectures outside TGI's optimized list"], "when_to_choose": ["you need a production-ready, battle-tested LLM serving stack with Prometheus metrics and tracing", "you want an OpenAI Chat Completion-compatible API for open models", "you need multi-GPU tensor parallelism and quantization support", "you are deploying on Nvidia, AMD, Intel Gaudi, or AWS Inferentia hardware"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/text-generation-inference", "repo": "huggingface/text-generation-inference", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.603621+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:17:26.510223+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "729dcd84277b7ca98133a67c3a77777202dcc341d5f1efdda3588d77a458c2c8", "fetched_at": "2026-08-28T04:10:44.603621+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/text-generation-inference"}, {"content_hash": "1b08ae48e895a4e79f3e9be19e1ee6f211b35b936153ed376ff2723a946d8536", "fetched_at": "2026-08-29T08:16:26.705798+00:00", "kind": "homepage", "missing": false, "url": "http://hf.co/docs/text-generation-inference"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T08:16:26.709575+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "cf72731fd6c7e65aad0fbebf15fe468850198fed60be698747dc56fc52ea5ba0", "fetched_at": "2026-08-29T08:16:26.714209+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/quicktour"}, {"content_hash": "279b27da9308f248109ac8e6e6031504aa86e9d52ddd00cff0163caa105e711f", "fetched_at": "2026-08-29T08:16:26.715927+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/supported_models"}, {"content_hash": "35437bb2928f097f563c18dd316b34fc5af7512a1f8068b9c90f7b8e8aadfa0f", "fetched_at": "2026-08-29T08:16:26.717666+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_nvidia"}, {"content_hash": "34b42bf3691bf5bf36e139f457a261d60068228e1d7c4857c874e3d2f81b8d75", "fetched_at": "2026-08-29T08:16:26.719744+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_amd"}, {"content_hash": "13e741593c24e83a5ab473178d4012dfdfa0e8355d263983adc46978274dd4a9", "fetched_at": "2026-08-29T08:16:26.721371+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_gaudi"}, {"content_hash": "58a62cfd3396012da94bb63e6a72702a9fc1d1cc43cf731770e1b55b7a3505d7", "fetched_at": "2026-08-29T08:16:26.723233+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_inferentia"}, {"content_hash": "de6b7a178be544927ffd2e1990e33adcbee1bf54f7edf74da0714c6a3803ec65", "fetched_at": "2026-08-29T08:16:26.712093+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/pricing"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.603621+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:17:26.510223+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "729dcd84277b7ca98133a67c3a77777202dcc341d5f1efdda3588d77a458c2c8", "fetched_at": "2026-08-28T04:10:44.603621+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/text-generation-inference"}, {"content_hash": "1b08ae48e895a4e79f3e9be19e1ee6f211b35b936153ed376ff2723a946d8536", "fetched_at": "2026-08-29T08:16:26.705798+00:00", "kind": "homepage", "missing": false, "url": "http://hf.co/docs/text-generation-inference"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T08:16:26.709575+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "cf72731fd6c7e65aad0fbebf15fe468850198fed60be698747dc56fc52ea5ba0", "fetched_at": "2026-08-29T08:16:26.714209+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/quicktour"}, {"content_hash": "279b27da9308f248109ac8e6e6031504aa86e9d52ddd00cff0163caa105e711f", "fetched_at": "2026-08-29T08:16:26.715927+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/supported_models"}, {"content_hash": "35437bb2928f097f563c18dd316b34fc5af7512a1f8068b9c90f7b8e8aadfa0f", "fetched_at": "2026-08-29T08:16:26.717666+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_nvidia"}, {"content_hash": "34b42bf3691bf5bf36e139f457a261d60068228e1d7c4857c874e3d2f81b8d75", "fetched_at": "2026-08-29T08:16:26.719744+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_amd"}, {"content_hash": "13e741593c24e83a5ab473178d4012dfdfa0e8355d263983adc46978274dd4a9", "fetched_at": "2026-08-29T08:16:26.721371+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_gaudi"}, {"content_hash": "58a62cfd3396012da94bb63e6a72702a9fc1d1cc43cf731770e1b55b7a3505d7", "fetched_at": "2026-08-29T08:16:26.723233+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_inferentia"}, {"content_hash": "de6b7a178be544927ffd2e1990e33adcbee1bf54f7edf74da0714c6a3803ec65", "fetched_at": "2026-08-29T08:16:26.712093+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/pricing"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:17:26.510223+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "729dcd84277b7ca98133a67c3a77777202dcc341d5f1efdda3588d77a458c2c8", "fetched_at": "2026-08-28T04:10:44.603621+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/text-generation-inference"}, {"content_hash": "1b08ae48e895a4e79f3e9be19e1ee6f211b35b936153ed376ff2723a946d8536", "fetched_at": "2026-08-29T08:16:26.705798+00:00", "kind": "homepage", "missing": false, "url": "http://hf.co/docs/text-generation-inference"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T08:16:26.709575+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "cf72731fd6c7e65aad0fbebf15fe468850198fed60be698747dc56fc52ea5ba0", "fetched_at": "2026-08-29T08:16:26.714209+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/quicktour"}, {"content_hash": "279b27da9308f248109ac8e6e6031504aa86e9d52ddd00cff0163caa105e711f", "fetched_at": "2026-08-29T08:16:26.715927+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/supported_models"}, {"content_hash": "35437bb2928f097f563c18dd316b34fc5af7512a1f8068b9c90f7b8e8aadfa0f", "fetched_at": "2026-08-29T08:16:26.717666+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_nvidia"}, {"content_hash": "34b42bf3691bf5bf36e139f457a261d60068228e1d7c4857c874e3d2f81b8d75", "fetched_at": "2026-08-29T08:16:26.719744+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_amd"}, {"content_hash": "13e741593c24e83a5ab473178d4012dfdfa0e8355d263983adc46978274dd4a9", "fetched_at": "2026-08-29T08:16:26.721371+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_gaudi"}, {"content_hash": "58a62cfd3396012da94bb63e6a72702a9fc1d1cc43cf731770e1b55b7a3505d7", "fetched_at": "2026-08-29T08:16:26.723233+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_inferentia"}, {"content_hash": "de6b7a178be544927ffd2e1990e33adcbee1bf54f7edf74da0714c6a3803ec65", "fetched_at": "2026-08-29T08:16:26.712093+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/pricing"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.603621+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.603621+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.603621+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:17:26.510223+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "729dcd84277b7ca98133a67c3a77777202dcc341d5f1efdda3588d77a458c2c8", "fetched_at": "2026-08-28T04:10:44.603621+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/text-generation-inference"}, {"content_hash": "1b08ae48e895a4e79f3e9be19e1ee6f211b35b936153ed376ff2723a946d8536", "fetched_at": "2026-08-29T08:16:26.705798+00:00", "kind": "homepage", "missing": false, "url": "http://hf.co/docs/text-generation-inference"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T08:16:26.709575+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "cf72731fd6c7e65aad0fbebf15fe468850198fed60be698747dc56fc52ea5ba0", "fetched_at": "2026-08-29T08:16:26.714209+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/quicktour"}, {"content_hash": "279b27da9308f248109ac8e6e6031504aa86e9d52ddd00cff0163caa105e711f", "fetched_at": "2026-08-29T08:16:26.715927+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/supported_models"}, {"content_hash": "35437bb2928f097f563c18dd316b34fc5af7512a1f8068b9c90f7b8e8aadfa0f", "fetched_at": "2026-08-29T08:16:26.717666+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_nvidia"}, {"content_hash": "34b42bf3691bf5bf36e139f457a261d60068228e1d7c4857c874e3d2f81b8d75", "fetched_at": "2026-08-29T08:16:26.719744+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_amd"}, {"content_hash": "13e741593c24e83a5ab473178d4012dfdfa0e8355d263983adc46978274dd4a9", "fetched_at": "2026-08-29T08:16:26.721371+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_gaudi"}, {"content_hash": "58a62cfd3396012da94bb63e6a72702a9fc1d1cc43cf731770e1b55b7a3505d7", "fetched_at": "2026-08-29T08:16:26.723233+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_inferentia"}, {"content_hash": "de6b7a178be544927ffd2e1990e33adcbee1bf54f7edf74da0714c6a3803ec65", "fetched_at": "2026-08-29T08:16:26.712093+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/pricing"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.603621+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.603621+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:17:26.510223+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "729dcd84277b7ca98133a67c3a77777202dcc341d5f1efdda3588d77a458c2c8", "fetched_at": "2026-08-28T04:10:44.603621+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/text-generation-inference"}, {"content_hash": "1b08ae48e895a4e79f3e9be19e1ee6f211b35b936153ed376ff2723a946d8536", "fetched_at": "2026-08-29T08:16:26.705798+00:00", "kind": "homepage", "missing": false, "url": "http://hf.co/docs/text-generation-inference"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T08:16:26.709575+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "cf72731fd6c7e65aad0fbebf15fe468850198fed60be698747dc56fc52ea5ba0", "fetched_at": "2026-08-29T08:16:26.714209+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/quicktour"}, {"content_hash": "279b27da9308f248109ac8e6e6031504aa86e9d52ddd00cff0163caa105e711f", "fetched_at": "2026-08-29T08:16:26.715927+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/supported_models"}, {"content_hash": "35437bb2928f097f563c18dd316b34fc5af7512a1f8068b9c90f7b8e8aadfa0f", "fetched_at": "2026-08-29T08:16:26.717666+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_nvidia"}, {"content_hash": "34b42bf3691bf5bf36e139f457a261d60068228e1d7c4857c874e3d2f81b8d75", "fetched_at": "2026-08-29T08:16:26.719744+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_amd"}, {"content_hash": "13e741593c24e83a5ab473178d4012dfdfa0e8355d263983adc46978274dd4a9", "fetched_at": "2026-08-29T08:16:26.721371+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_gaudi"}, {"content_hash": "58a62cfd3396012da94bb63e6a72702a9fc1d1cc43cf731770e1b55b7a3505d7", "fetched_at": "2026-08-29T08:16:26.723233+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_inferentia"}, {"content_hash": "de6b7a178be544927ffd2e1990e33adcbee1bf54f7edf74da0714c6a3803ec65", "fetched_at": "2026-08-29T08:16:26.712093+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/pricing"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.603621+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.603621+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.603621+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:17:26.510223+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "729dcd84277b7ca98133a67c3a77777202dcc341d5f1efdda3588d77a458c2c8", "fetched_at": "2026-08-28T04:10:44.603621+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/text-generation-inference"}, {"content_hash": "1b08ae48e895a4e79f3e9be19e1ee6f211b35b936153ed376ff2723a946d8536", "fetched_at": "2026-08-29T08:16:26.705798+00:00", "kind": "homepage", "missing": false, "url": "http://hf.co/docs/text-generation-inference"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T08:16:26.709575+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "cf72731fd6c7e65aad0fbebf15fe468850198fed60be698747dc56fc52ea5ba0", "fetched_at": "2026-08-29T08:16:26.714209+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/quicktour"}, {"content_hash": "279b27da9308f248109ac8e6e6031504aa86e9d52ddd00cff0163caa105e711f", "fetched_at": "2026-08-29T08:16:26.715927+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/supported_models"}, {"content_hash": "35437bb2928f097f563c18dd316b34fc5af7512a1f8068b9c90f7b8e8aadfa0f", "fetched_at": "2026-08-29T08:16:26.717666+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_nvidia"}, {"content_hash": "34b42bf3691bf5bf36e139f457a261d60068228e1d7c4857c874e3d2f81b8d75", "fetched_at": "2026-08-29T08:16:26.719744+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_amd"}, {"content_hash": "13e741593c24e83a5ab473178d4012dfdfa0e8355d263983adc46978274dd4a9", "fetched_at": "2026-08-29T08:16:26.721371+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_gaudi"}, {"content_hash": "58a62cfd3396012da94bb63e6a72702a9fc1d1cc43cf731770e1b55b7a3505d7", "fetched_at": "2026-08-29T08:16:26.723233+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_inferentia"}, {"content_hash": "de6b7a178be544927ffd2e1990e33adcbee1bf54f7edf74da0714c6a3803ec65", "fetched_at": "2026-08-29T08:16:26.712093+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/pricing"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.603621+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:44.603621+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:17:26.510223+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "729dcd84277b7ca98133a67c3a77777202dcc341d5f1efdda3588d77a458c2c8", "fetched_at": "2026-08-28T04:10:44.603621+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/text-generation-inference"}, {"content_hash": "1b08ae48e895a4e79f3e9be19e1ee6f211b35b936153ed376ff2723a946d8536", "fetched_at": "2026-08-29T08:16:26.705798+00:00", "kind": "homepage", "missing": false, "url": "http://hf.co/docs/text-generation-inference"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T08:16:26.709575+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "cf72731fd6c7e65aad0fbebf15fe468850198fed60be698747dc56fc52ea5ba0", "fetched_at": "2026-08-29T08:16:26.714209+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/quicktour"}, {"content_hash": "279b27da9308f248109ac8e6e6031504aa86e9d52ddd00cff0163caa105e711f", "fetched_at": "2026-08-29T08:16:26.715927+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/supported_models"}, {"content_hash": "35437bb2928f097f563c18dd316b34fc5af7512a1f8068b9c90f7b8e8aadfa0f", "fetched_at": "2026-08-29T08:16:26.717666+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_nvidia"}, {"content_hash": "34b42bf3691bf5bf36e139f457a261d60068228e1d7c4857c874e3d2f81b8d75", "fetched_at": "2026-08-29T08:16:26.719744+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_amd"}, {"content_hash": "13e741593c24e83a5ab473178d4012dfdfa0e8355d263983adc46978274dd4a9", "fetched_at": "2026-08-29T08:16:26.721371+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_gaudi"}, {"content_hash": "58a62cfd3396012da94bb63e6a72702a9fc1d1cc43cf731770e1b55b7a3505d7", "fetched_at": "2026-08-29T08:16:26.723233+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_inferentia"}, {"content_hash": "de6b7a178be544927ffd2e1990e33adcbee1bf54f7edf74da0714c6a3803ec65", "fetched_at": "2026-08-29T08:16:26.712093+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/pricing"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:17:26.510223+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "729dcd84277b7ca98133a67c3a77777202dcc341d5f1efdda3588d77a458c2c8", "fetched_at": "2026-08-28T04:10:44.603621+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/text-generation-inference"}, {"content_hash": "1b08ae48e895a4e79f3e9be19e1ee6f211b35b936153ed376ff2723a946d8536", "fetched_at": "2026-08-29T08:16:26.705798+00:00", "kind": "homepage", "missing": false, "url": "http://hf.co/docs/text-generation-inference"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T08:16:26.709575+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "cf72731fd6c7e65aad0fbebf15fe468850198fed60be698747dc56fc52ea5ba0", "fetched_at": "2026-08-29T08:16:26.714209+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/quicktour"}, {"content_hash": "279b27da9308f248109ac8e6e6031504aa86e9d52ddd00cff0163caa105e711f", "fetched_at": "2026-08-29T08:16:26.715927+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/supported_models"}, {"content_hash": "35437bb2928f097f563c18dd316b34fc5af7512a1f8068b9c90f7b8e8aadfa0f", "fetched_at": "2026-08-29T08:16:26.717666+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_nvidia"}, {"content_hash": "34b42bf3691bf5bf36e139f457a261d60068228e1d7c4857c874e3d2f81b8d75", "fetched_at": "2026-08-29T08:16:26.719744+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_amd"}, {"content_hash": "13e741593c24e83a5ab473178d4012dfdfa0e8355d263983adc46978274dd4a9", "fetched_at": "2026-08-29T08:16:26.721371+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_gaudi"}, {"content_hash": "58a62cfd3396012da94bb63e6a72702a9fc1d1cc43cf731770e1b55b7a3505d7", "fetched_at": "2026-08-29T08:16:26.723233+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_inferentia"}, {"content_hash": "de6b7a178be544927ffd2e1990e33adcbee1bf54f7edf74da0714c6a3803ec65", "fetched_at": "2026-08-29T08:16:26.712093+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/pricing"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:17:26.510223+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "729dcd84277b7ca98133a67c3a77777202dcc341d5f1efdda3588d77a458c2c8", "fetched_at": "2026-08-28T04:10:44.603621+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/text-generation-inference"}, {"content_hash": "1b08ae48e895a4e79f3e9be19e1ee6f211b35b936153ed376ff2723a946d8536", "fetched_at": "2026-08-29T08:16:26.705798+00:00", "kind": "homepage", "missing": false, "url": "http://hf.co/docs/text-generation-inference"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T08:16:26.709575+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "cf72731fd6c7e65aad0fbebf15fe468850198fed60be698747dc56fc52ea5ba0", "fetched_at": "2026-08-29T08:16:26.714209+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/quicktour"}, {"content_hash": "279b27da9308f248109ac8e6e6031504aa86e9d52ddd00cff0163caa105e711f", "fetched_at": "2026-08-29T08:16:26.715927+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/supported_models"}, {"content_hash": "35437bb2928f097f563c18dd316b34fc5af7512a1f8068b9c90f7b8e8aadfa0f", "fetched_at": "2026-08-29T08:16:26.717666+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_nvidia"}, {"content_hash": "34b42bf3691bf5bf36e139f457a261d60068228e1d7c4857c874e3d2f81b8d75", "fetched_at": "2026-08-29T08:16:26.719744+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_amd"}, {"content_hash": "13e741593c24e83a5ab473178d4012dfdfa0e8355d263983adc46978274dd4a9", "fetched_at": "2026-08-29T08:16:26.721371+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_gaudi"}, {"content_hash": "58a62cfd3396012da94bb63e6a72702a9fc1d1cc43cf731770e1b55b7a3505d7", "fetched_at": "2026-08-29T08:16:26.723233+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_inferentia"}, {"content_hash": "de6b7a178be544927ffd2e1990e33adcbee1bf54f7edf74da0714c6a3803ec65", "fetched_at": "2026-08-29T08:16:26.712093+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/pricing"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:17:26.510223+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "729dcd84277b7ca98133a67c3a77777202dcc341d5f1efdda3588d77a458c2c8", "fetched_at": "2026-08-28T04:10:44.603621+00:00", "kind": "readme", "missing": false, "url": "https://github.com/huggingface/text-generation-inference"}, {"content_hash": "1b08ae48e895a4e79f3e9be19e1ee6f211b35b936153ed376ff2723a946d8536", "fetched_at": "2026-08-29T08:16:26.705798+00:00", "kind": "homepage", "missing": false, "url": "http://hf.co/docs/text-generation-inference"}, {"content_hash": "bdec26667b98a2700d86b15044cf944ca1f17f4ab8579c3d27a3e627603b9ae8", "fetched_at": "2026-08-29T08:16:26.709575+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs"}, {"content_hash": "cf72731fd6c7e65aad0fbebf15fe468850198fed60be698747dc56fc52ea5ba0", "fetched_at": "2026-08-29T08:16:26.714209+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/quicktour"}, {"content_hash": "279b27da9308f248109ac8e6e6031504aa86e9d52ddd00cff0163caa105e711f", "fetched_at": "2026-08-29T08:16:26.715927+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/supported_models"}, {"content_hash": "35437bb2928f097f563c18dd316b34fc5af7512a1f8068b9c90f7b8e8aadfa0f", "fetched_at": "2026-08-29T08:16:26.717666+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_nvidia"}, {"content_hash": "34b42bf3691bf5bf36e139f457a261d60068228e1d7c4857c874e3d2f81b8d75", "fetched_at": "2026-08-29T08:16:26.719744+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_amd"}, {"content_hash": "13e741593c24e83a5ab473178d4012dfdfa0e8355d263983adc46978274dd4a9", "fetched_at": "2026-08-29T08:16:26.721371+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_gaudi"}, {"content_hash": "58a62cfd3396012da94bb63e6a72702a9fc1d1cc43cf731770e1b55b7a3505d7", "fetched_at": "2026-08-29T08:16:26.723233+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/docs/text-generation-inference/installation_inferentia"}, {"content_hash": "de6b7a178be544927ffd2e1990e33adcbee1bf54f7edf74da0714c6a3803ec65", "fetched_at": "2026-08-29T08:16:26.712093+00:00", "kind": "site_page", "missing": false, "url": "https://huggingface.co/pricing"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 73, "longevity": 100, "rhythm": 62}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1425, "days_push": 165, "days_rel": 257, "gap_med": 15.5, "n_releases_24m": 21}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}