{"adoption": {"forks": 706, "observed_at": "2026-08-28T04:08:37.694757+00:00", "stars": 4164}, "canonical_url": "https://ross.abutalabs.com/products/llm-d", "card": {"archived": false, "artifact_type": "framework", "description": "Achieve state of the art inference performance with modern accelerators on Kubernetes", "domain": ["large-language-models", "machine-learning", "gpu-computing", "cloud-computing", "microservices", "infrastructure-as-code"], "enriched": true, "function": ["llm-inference", "api-gateway", "load-testing", "caching", "monitoring", "deployment", "container-orchestration"], "health_score": 100, "homepage": "https://www.llm-d.ai", "language": "Shell", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["llm-d/llm-d"], "name": "llm-d/llm-d", "platform": ["cloud", "self-hosted", "go", "python"], "pushed_at": "2026-08-26T22:59:24+00:00", "repo": "llm-d/llm-d", "stars": 4164, "tags": ["distributed-inference", "kv-cache", "vllm", "sglang", "intelligent-routing", "prefix-cache", "moe", "cncf-sandbox", "helm-charts", "autoscaling", "gateway-api-inference-extension", "containers", "kubernetes", "docker", "gpu"], "topics": ["ai", "cncf", "distributed-inference", "gpu", "inference", "intelligent-routing", "kubernetes", "llm", "model-server"], "urls": [], "use_cases": ["serve llm inference at scale on kubernetes", "route requests by prefix cache affinity", "deploy deepseek-r1 with wide expert parallelism", "autoscale llm inference pool based on slo", "offload kv cache to cpu and disk", "run vllm across multiple gpus in production", "reduce time to first token for multi-turn chat", "batch offline inference with openai-compatible api"], "what_it_is": "llm-d is a Kubernetes-native distributed LLM inference serving stack that orchestrates model servers like vLLM and SGLang across clusters. It provides intelligent prefix-cache and load-aware routing, tiered KV-cache management, prefill/decode disaggregation, wide expert parallelism, and SLO-aware autoscaling, packaged as tested 'Well-Lit Path' Helm deployment recipes.", "when_to_avoid": ["you serve a single model on one node and vanilla vLLM or SGLang meets your needs", "you have no Kubernetes infrastructure and don't want to adopt it", "you need a simple managed API endpoint rather than operating your own inference cluster"], "when_to_choose": ["you already run Kubernetes and want production-grade distributed LLM serving on GPUs, TPUs, or other accelerators", "you need LLM-aware load balancing, KV-cache reuse, or disaggregated prefill/decode beyond what a single vLLM/SGLang node provides", "you want vendor-neutral, engine-agnostic orchestration with tested deployment recipes and benchmarks"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/llm-d", "repo": "llm-d/llm-d", "role": "main", "score": 82}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:37.694757+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:22:47.453709+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b0c6d70bb3c337fec500a8e52f9713d41e785ccd143799e2f607cb5fb7e632bb", "fetched_at": "2026-08-28T04:08:37.694757+00:00", "kind": "readme", "missing": false, "url": "https://github.com/llm-d/llm-d"}, {"content_hash": "b60fc371f22834f4ec8a2ea69723a75655850e716e9f3339923a000a2fd581e6", "fetched_at": "2026-08-29T09:13:42.091244+00:00", "kind": "homepage", "missing": false, "url": "https://www.llm-d.ai"}, {"content_hash": "02d870a95c0f6773cdaae18833a9b10a4187184a53af7cfd79638570cbbd1ac7", "fetched_at": "2026-08-29T09:13:42.100078+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/getting-started/quickstart"}, {"content_hash": "1e00c66d239728c9a79816778e47a83d7e8a180023c5b59b2cdbeb54d8f6fd86", "fetched_at": "2026-08-29T09:13:42.101955+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs"}, {"content_hash": "1d40cbf5dfd6a9b6bcaf1aac2d69759e7b8fdd100b8c8728917f365980180e03", "fetched_at": "2026-08-29T09:13:42.103501+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/0.8"}, {"content_hash": "c81c2da56f78fd2375b59dd56810898cb668bab6931d671dde643d91ea1f69e1", "fetched_at": "2026-08-29T09:13:42.105025+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/0.7"}, {"content_hash": "54f751bb69db9ad9ad257c940f963d202380a0f16c7f7e6b47fb85fb76152160", "fetched_at": "2026-08-29T09:13:42.106810+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/dev"}, {"content_hash": "3a28a2cbb49b2bf5506b3e2f316ec9433af9492a25a7e679c9a264e4df3ccb4d", "fetched_at": "2026-08-29T09:13:42.108359+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/optimized-baseline"}, {"content_hash": "9510eedda65aa24711b98b4b1929d8f6a1b9380e20746c412ea51355a158fc6e", "fetched_at": "2026-08-29T09:13:42.110140+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/predicted-latency"}, {"content_hash": "cd39e1aaff993d94d8b7a450212f473ffa5ba553137ec8457f6829df1b3b4b78", "fetched_at": "2026-08-29T09:13:42.111912+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/precise-prefix-cache-routing"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:37.694757+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:22:47.453709+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b0c6d70bb3c337fec500a8e52f9713d41e785ccd143799e2f607cb5fb7e632bb", "fetched_at": "2026-08-28T04:08:37.694757+00:00", "kind": "readme", "missing": false, "url": "https://github.com/llm-d/llm-d"}, {"content_hash": "b60fc371f22834f4ec8a2ea69723a75655850e716e9f3339923a000a2fd581e6", "fetched_at": "2026-08-29T09:13:42.091244+00:00", "kind": "homepage", "missing": false, "url": "https://www.llm-d.ai"}, {"content_hash": "02d870a95c0f6773cdaae18833a9b10a4187184a53af7cfd79638570cbbd1ac7", "fetched_at": "2026-08-29T09:13:42.100078+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/getting-started/quickstart"}, {"content_hash": "1e00c66d239728c9a79816778e47a83d7e8a180023c5b59b2cdbeb54d8f6fd86", "fetched_at": "2026-08-29T09:13:42.101955+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs"}, {"content_hash": "1d40cbf5dfd6a9b6bcaf1aac2d69759e7b8fdd100b8c8728917f365980180e03", "fetched_at": "2026-08-29T09:13:42.103501+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/0.8"}, {"content_hash": "c81c2da56f78fd2375b59dd56810898cb668bab6931d671dde643d91ea1f69e1", "fetched_at": "2026-08-29T09:13:42.105025+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/0.7"}, {"content_hash": "54f751bb69db9ad9ad257c940f963d202380a0f16c7f7e6b47fb85fb76152160", "fetched_at": "2026-08-29T09:13:42.106810+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/dev"}, {"content_hash": "3a28a2cbb49b2bf5506b3e2f316ec9433af9492a25a7e679c9a264e4df3ccb4d", "fetched_at": "2026-08-29T09:13:42.108359+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/optimized-baseline"}, {"content_hash": "9510eedda65aa24711b98b4b1929d8f6a1b9380e20746c412ea51355a158fc6e", "fetched_at": "2026-08-29T09:13:42.110140+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/predicted-latency"}, {"content_hash": "cd39e1aaff993d94d8b7a450212f473ffa5ba553137ec8457f6829df1b3b4b78", "fetched_at": "2026-08-29T09:13:42.111912+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/precise-prefix-cache-routing"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:22:47.453709+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b0c6d70bb3c337fec500a8e52f9713d41e785ccd143799e2f607cb5fb7e632bb", "fetched_at": "2026-08-28T04:08:37.694757+00:00", "kind": "readme", "missing": false, "url": "https://github.com/llm-d/llm-d"}, {"content_hash": "b60fc371f22834f4ec8a2ea69723a75655850e716e9f3339923a000a2fd581e6", "fetched_at": "2026-08-29T09:13:42.091244+00:00", "kind": "homepage", "missing": false, "url": "https://www.llm-d.ai"}, {"content_hash": "02d870a95c0f6773cdaae18833a9b10a4187184a53af7cfd79638570cbbd1ac7", "fetched_at": "2026-08-29T09:13:42.100078+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/getting-started/quickstart"}, {"content_hash": "1e00c66d239728c9a79816778e47a83d7e8a180023c5b59b2cdbeb54d8f6fd86", "fetched_at": "2026-08-29T09:13:42.101955+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs"}, {"content_hash": "1d40cbf5dfd6a9b6bcaf1aac2d69759e7b8fdd100b8c8728917f365980180e03", "fetched_at": "2026-08-29T09:13:42.103501+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/0.8"}, {"content_hash": "c81c2da56f78fd2375b59dd56810898cb668bab6931d671dde643d91ea1f69e1", "fetched_at": "2026-08-29T09:13:42.105025+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/0.7"}, {"content_hash": "54f751bb69db9ad9ad257c940f963d202380a0f16c7f7e6b47fb85fb76152160", "fetched_at": "2026-08-29T09:13:42.106810+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/dev"}, {"content_hash": "3a28a2cbb49b2bf5506b3e2f316ec9433af9492a25a7e679c9a264e4df3ccb4d", "fetched_at": "2026-08-29T09:13:42.108359+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/optimized-baseline"}, {"content_hash": "9510eedda65aa24711b98b4b1929d8f6a1b9380e20746c412ea51355a158fc6e", "fetched_at": "2026-08-29T09:13:42.110140+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/predicted-latency"}, {"content_hash": "cd39e1aaff993d94d8b7a450212f473ffa5ba553137ec8457f6829df1b3b4b78", "fetched_at": "2026-08-29T09:13:42.111912+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/precise-prefix-cache-routing"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:37.694757+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:37.694757+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:37.694757+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:22:47.453709+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b0c6d70bb3c337fec500a8e52f9713d41e785ccd143799e2f607cb5fb7e632bb", "fetched_at": "2026-08-28T04:08:37.694757+00:00", "kind": "readme", "missing": false, "url": "https://github.com/llm-d/llm-d"}, {"content_hash": "b60fc371f22834f4ec8a2ea69723a75655850e716e9f3339923a000a2fd581e6", "fetched_at": "2026-08-29T09:13:42.091244+00:00", "kind": "homepage", "missing": false, "url": "https://www.llm-d.ai"}, {"content_hash": "02d870a95c0f6773cdaae18833a9b10a4187184a53af7cfd79638570cbbd1ac7", "fetched_at": "2026-08-29T09:13:42.100078+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/getting-started/quickstart"}, {"content_hash": "1e00c66d239728c9a79816778e47a83d7e8a180023c5b59b2cdbeb54d8f6fd86", "fetched_at": "2026-08-29T09:13:42.101955+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs"}, {"content_hash": "1d40cbf5dfd6a9b6bcaf1aac2d69759e7b8fdd100b8c8728917f365980180e03", "fetched_at": "2026-08-29T09:13:42.103501+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/0.8"}, {"content_hash": "c81c2da56f78fd2375b59dd56810898cb668bab6931d671dde643d91ea1f69e1", "fetched_at": "2026-08-29T09:13:42.105025+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/0.7"}, {"content_hash": "54f751bb69db9ad9ad257c940f963d202380a0f16c7f7e6b47fb85fb76152160", "fetched_at": "2026-08-29T09:13:42.106810+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/dev"}, {"content_hash": "3a28a2cbb49b2bf5506b3e2f316ec9433af9492a25a7e679c9a264e4df3ccb4d", "fetched_at": "2026-08-29T09:13:42.108359+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/optimized-baseline"}, {"content_hash": "9510eedda65aa24711b98b4b1929d8f6a1b9380e20746c412ea51355a158fc6e", "fetched_at": "2026-08-29T09:13:42.110140+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/predicted-latency"}, {"content_hash": "cd39e1aaff993d94d8b7a450212f473ffa5ba553137ec8457f6829df1b3b4b78", "fetched_at": "2026-08-29T09:13:42.111912+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/precise-prefix-cache-routing"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:37.694757+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:37.694757+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:22:47.453709+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b0c6d70bb3c337fec500a8e52f9713d41e785ccd143799e2f607cb5fb7e632bb", "fetched_at": "2026-08-28T04:08:37.694757+00:00", "kind": "readme", "missing": false, "url": "https://github.com/llm-d/llm-d"}, {"content_hash": "b60fc371f22834f4ec8a2ea69723a75655850e716e9f3339923a000a2fd581e6", "fetched_at": "2026-08-29T09:13:42.091244+00:00", "kind": "homepage", "missing": false, "url": "https://www.llm-d.ai"}, {"content_hash": "02d870a95c0f6773cdaae18833a9b10a4187184a53af7cfd79638570cbbd1ac7", "fetched_at": "2026-08-29T09:13:42.100078+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/getting-started/quickstart"}, {"content_hash": "1e00c66d239728c9a79816778e47a83d7e8a180023c5b59b2cdbeb54d8f6fd86", "fetched_at": "2026-08-29T09:13:42.101955+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs"}, {"content_hash": "1d40cbf5dfd6a9b6bcaf1aac2d69759e7b8fdd100b8c8728917f365980180e03", "fetched_at": "2026-08-29T09:13:42.103501+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/0.8"}, {"content_hash": "c81c2da56f78fd2375b59dd56810898cb668bab6931d671dde643d91ea1f69e1", "fetched_at": "2026-08-29T09:13:42.105025+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/0.7"}, {"content_hash": "54f751bb69db9ad9ad257c940f963d202380a0f16c7f7e6b47fb85fb76152160", "fetched_at": "2026-08-29T09:13:42.106810+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/dev"}, {"content_hash": "3a28a2cbb49b2bf5506b3e2f316ec9433af9492a25a7e679c9a264e4df3ccb4d", "fetched_at": "2026-08-29T09:13:42.108359+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/optimized-baseline"}, {"content_hash": "9510eedda65aa24711b98b4b1929d8f6a1b9380e20746c412ea51355a158fc6e", "fetched_at": "2026-08-29T09:13:42.110140+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/predicted-latency"}, {"content_hash": "cd39e1aaff993d94d8b7a450212f473ffa5ba553137ec8457f6829df1b3b4b78", "fetched_at": "2026-08-29T09:13:42.111912+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/precise-prefix-cache-routing"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:37.694757+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:37.694757+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:37.694757+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:22:47.453709+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b0c6d70bb3c337fec500a8e52f9713d41e785ccd143799e2f607cb5fb7e632bb", "fetched_at": "2026-08-28T04:08:37.694757+00:00", "kind": "readme", "missing": false, "url": "https://github.com/llm-d/llm-d"}, {"content_hash": "b60fc371f22834f4ec8a2ea69723a75655850e716e9f3339923a000a2fd581e6", "fetched_at": "2026-08-29T09:13:42.091244+00:00", "kind": "homepage", "missing": false, "url": "https://www.llm-d.ai"}, {"content_hash": "02d870a95c0f6773cdaae18833a9b10a4187184a53af7cfd79638570cbbd1ac7", "fetched_at": "2026-08-29T09:13:42.100078+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/getting-started/quickstart"}, {"content_hash": "1e00c66d239728c9a79816778e47a83d7e8a180023c5b59b2cdbeb54d8f6fd86", "fetched_at": "2026-08-29T09:13:42.101955+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs"}, {"content_hash": "1d40cbf5dfd6a9b6bcaf1aac2d69759e7b8fdd100b8c8728917f365980180e03", "fetched_at": "2026-08-29T09:13:42.103501+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/0.8"}, {"content_hash": "c81c2da56f78fd2375b59dd56810898cb668bab6931d671dde643d91ea1f69e1", "fetched_at": "2026-08-29T09:13:42.105025+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/0.7"}, {"content_hash": "54f751bb69db9ad9ad257c940f963d202380a0f16c7f7e6b47fb85fb76152160", "fetched_at": "2026-08-29T09:13:42.106810+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/dev"}, {"content_hash": "3a28a2cbb49b2bf5506b3e2f316ec9433af9492a25a7e679c9a264e4df3ccb4d", "fetched_at": "2026-08-29T09:13:42.108359+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/optimized-baseline"}, {"content_hash": "9510eedda65aa24711b98b4b1929d8f6a1b9380e20746c412ea51355a158fc6e", "fetched_at": "2026-08-29T09:13:42.110140+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/predicted-latency"}, {"content_hash": "cd39e1aaff993d94d8b7a450212f473ffa5ba553137ec8457f6829df1b3b4b78", "fetched_at": "2026-08-29T09:13:42.111912+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/precise-prefix-cache-routing"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:37.694757+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:37.694757+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:22:47.453709+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b0c6d70bb3c337fec500a8e52f9713d41e785ccd143799e2f607cb5fb7e632bb", "fetched_at": "2026-08-28T04:08:37.694757+00:00", "kind": "readme", "missing": false, "url": "https://github.com/llm-d/llm-d"}, {"content_hash": "b60fc371f22834f4ec8a2ea69723a75655850e716e9f3339923a000a2fd581e6", "fetched_at": "2026-08-29T09:13:42.091244+00:00", "kind": "homepage", "missing": false, "url": "https://www.llm-d.ai"}, {"content_hash": "02d870a95c0f6773cdaae18833a9b10a4187184a53af7cfd79638570cbbd1ac7", "fetched_at": "2026-08-29T09:13:42.100078+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/getting-started/quickstart"}, {"content_hash": "1e00c66d239728c9a79816778e47a83d7e8a180023c5b59b2cdbeb54d8f6fd86", "fetched_at": "2026-08-29T09:13:42.101955+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs"}, {"content_hash": "1d40cbf5dfd6a9b6bcaf1aac2d69759e7b8fdd100b8c8728917f365980180e03", "fetched_at": "2026-08-29T09:13:42.103501+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/0.8"}, {"content_hash": "c81c2da56f78fd2375b59dd56810898cb668bab6931d671dde643d91ea1f69e1", "fetched_at": "2026-08-29T09:13:42.105025+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/0.7"}, {"content_hash": "54f751bb69db9ad9ad257c940f963d202380a0f16c7f7e6b47fb85fb76152160", "fetched_at": "2026-08-29T09:13:42.106810+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/dev"}, {"content_hash": "3a28a2cbb49b2bf5506b3e2f316ec9433af9492a25a7e679c9a264e4df3ccb4d", "fetched_at": "2026-08-29T09:13:42.108359+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/optimized-baseline"}, {"content_hash": "9510eedda65aa24711b98b4b1929d8f6a1b9380e20746c412ea51355a158fc6e", "fetched_at": "2026-08-29T09:13:42.110140+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/predicted-latency"}, {"content_hash": "cd39e1aaff993d94d8b7a450212f473ffa5ba553137ec8457f6829df1b3b4b78", "fetched_at": "2026-08-29T09:13:42.111912+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/precise-prefix-cache-routing"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:22:47.453709+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b0c6d70bb3c337fec500a8e52f9713d41e785ccd143799e2f607cb5fb7e632bb", "fetched_at": "2026-08-28T04:08:37.694757+00:00", "kind": "readme", "missing": false, "url": "https://github.com/llm-d/llm-d"}, {"content_hash": "b60fc371f22834f4ec8a2ea69723a75655850e716e9f3339923a000a2fd581e6", "fetched_at": "2026-08-29T09:13:42.091244+00:00", "kind": "homepage", "missing": false, "url": "https://www.llm-d.ai"}, {"content_hash": "02d870a95c0f6773cdaae18833a9b10a4187184a53af7cfd79638570cbbd1ac7", "fetched_at": "2026-08-29T09:13:42.100078+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/getting-started/quickstart"}, {"content_hash": "1e00c66d239728c9a79816778e47a83d7e8a180023c5b59b2cdbeb54d8f6fd86", "fetched_at": "2026-08-29T09:13:42.101955+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs"}, {"content_hash": "1d40cbf5dfd6a9b6bcaf1aac2d69759e7b8fdd100b8c8728917f365980180e03", "fetched_at": "2026-08-29T09:13:42.103501+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/0.8"}, {"content_hash": "c81c2da56f78fd2375b59dd56810898cb668bab6931d671dde643d91ea1f69e1", "fetched_at": "2026-08-29T09:13:42.105025+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/0.7"}, {"content_hash": "54f751bb69db9ad9ad257c940f963d202380a0f16c7f7e6b47fb85fb76152160", "fetched_at": "2026-08-29T09:13:42.106810+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/dev"}, {"content_hash": "3a28a2cbb49b2bf5506b3e2f316ec9433af9492a25a7e679c9a264e4df3ccb4d", "fetched_at": "2026-08-29T09:13:42.108359+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/optimized-baseline"}, {"content_hash": "9510eedda65aa24711b98b4b1929d8f6a1b9380e20746c412ea51355a158fc6e", "fetched_at": "2026-08-29T09:13:42.110140+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/predicted-latency"}, {"content_hash": "cd39e1aaff993d94d8b7a450212f473ffa5ba553137ec8457f6829df1b3b4b78", "fetched_at": "2026-08-29T09:13:42.111912+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/precise-prefix-cache-routing"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:22:47.453709+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b0c6d70bb3c337fec500a8e52f9713d41e785ccd143799e2f607cb5fb7e632bb", "fetched_at": "2026-08-28T04:08:37.694757+00:00", "kind": "readme", "missing": false, "url": "https://github.com/llm-d/llm-d"}, {"content_hash": "b60fc371f22834f4ec8a2ea69723a75655850e716e9f3339923a000a2fd581e6", "fetched_at": "2026-08-29T09:13:42.091244+00:00", "kind": "homepage", "missing": false, "url": "https://www.llm-d.ai"}, {"content_hash": "02d870a95c0f6773cdaae18833a9b10a4187184a53af7cfd79638570cbbd1ac7", "fetched_at": "2026-08-29T09:13:42.100078+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/getting-started/quickstart"}, {"content_hash": "1e00c66d239728c9a79816778e47a83d7e8a180023c5b59b2cdbeb54d8f6fd86", "fetched_at": "2026-08-29T09:13:42.101955+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs"}, {"content_hash": "1d40cbf5dfd6a9b6bcaf1aac2d69759e7b8fdd100b8c8728917f365980180e03", "fetched_at": "2026-08-29T09:13:42.103501+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/0.8"}, {"content_hash": "c81c2da56f78fd2375b59dd56810898cb668bab6931d671dde643d91ea1f69e1", "fetched_at": "2026-08-29T09:13:42.105025+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/0.7"}, {"content_hash": "54f751bb69db9ad9ad257c940f963d202380a0f16c7f7e6b47fb85fb76152160", "fetched_at": "2026-08-29T09:13:42.106810+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/dev"}, {"content_hash": "3a28a2cbb49b2bf5506b3e2f316ec9433af9492a25a7e679c9a264e4df3ccb4d", "fetched_at": "2026-08-29T09:13:42.108359+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/optimized-baseline"}, {"content_hash": "9510eedda65aa24711b98b4b1929d8f6a1b9380e20746c412ea51355a158fc6e", "fetched_at": "2026-08-29T09:13:42.110140+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/predicted-latency"}, {"content_hash": "cd39e1aaff993d94d8b7a450212f473ffa5ba553137ec8457f6829df1b3b4b78", "fetched_at": "2026-08-29T09:13:42.111912+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/precise-prefix-cache-routing"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:22:47.453709+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b0c6d70bb3c337fec500a8e52f9713d41e785ccd143799e2f607cb5fb7e632bb", "fetched_at": "2026-08-28T04:08:37.694757+00:00", "kind": "readme", "missing": false, "url": "https://github.com/llm-d/llm-d"}, {"content_hash": "b60fc371f22834f4ec8a2ea69723a75655850e716e9f3339923a000a2fd581e6", "fetched_at": "2026-08-29T09:13:42.091244+00:00", "kind": "homepage", "missing": false, "url": "https://www.llm-d.ai"}, {"content_hash": "02d870a95c0f6773cdaae18833a9b10a4187184a53af7cfd79638570cbbd1ac7", "fetched_at": "2026-08-29T09:13:42.100078+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/getting-started/quickstart"}, {"content_hash": "1e00c66d239728c9a79816778e47a83d7e8a180023c5b59b2cdbeb54d8f6fd86", "fetched_at": "2026-08-29T09:13:42.101955+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs"}, {"content_hash": "1d40cbf5dfd6a9b6bcaf1aac2d69759e7b8fdd100b8c8728917f365980180e03", "fetched_at": "2026-08-29T09:13:42.103501+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/0.8"}, {"content_hash": "c81c2da56f78fd2375b59dd56810898cb668bab6931d671dde643d91ea1f69e1", "fetched_at": "2026-08-29T09:13:42.105025+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/0.7"}, {"content_hash": "54f751bb69db9ad9ad257c940f963d202380a0f16c7f7e6b47fb85fb76152160", "fetched_at": "2026-08-29T09:13:42.106810+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/dev"}, {"content_hash": "3a28a2cbb49b2bf5506b3e2f316ec9433af9492a25a7e679c9a264e4df3ccb4d", "fetched_at": "2026-08-29T09:13:42.108359+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/optimized-baseline"}, {"content_hash": "9510eedda65aa24711b98b4b1929d8f6a1b9380e20746c412ea51355a158fc6e", "fetched_at": "2026-08-29T09:13:42.110140+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/predicted-latency"}, {"content_hash": "cd39e1aaff993d94d8b7a450212f473ffa5ba553137ec8457f6829df1b3b4b78", "fetched_at": "2026-08-29T09:13:42.111912+00:00", "kind": "site_page", "missing": false, "url": "https://llm-d.ai/docs/well-lit-paths/foundations/precise-prefix-cache-routing"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 35, "rhythm": 86}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 491, "days_push": 7, "days_rel": 16, "gap_med": 34.0, "n_releases_24m": 11}, "score": 82, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}