{"adoption": {"forks": 1132, "observed_at": "2026-08-28T04:09:43.056954+00:00", "stars": 6398}, "canonical_url": "https://ross.abutalabs.com/products/mooncake", "card": {"archived": false, "artifact_type": "service", "description": "Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.", "domain": ["large-language-models", "artificial-intelligence", "microservices", "gpu-computing", "infrastructure-as-code"], "enriched": true, "function": ["llm-inference", "caching", "gpu-computing", "streaming", "scheduling"], "health_score": 100, "homepage": "https://kvcache-ai.github.io/Mooncake/", "language": "C++", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["kvcache-ai/Mooncake"], "name": "kvcache-ai/Mooncake", "platform": ["cpp", "python", "self-hosted"], "pushed_at": "2026-08-26T12:04:34+00:00", "repo": "kvcache-ai/Mooncake", "stars": 6398, "tags": ["kvcache", "rdma", "disaggregation", "prefill-decode-separation", "vllm", "sglang", "kv-cache-pool", "llm-serving", "linux", "docker", "gpu"], "topics": ["inference", "kvcache", "llm", "rdma", "sglang", "vllm", "disaggregation", "tokenspeed", "reinforcement-learning", "trt-llm"], "urls": [], "use_cases": ["serve LLMs with high throughput under SLO constraints", "build a distributed KVCache pool for vLLM or SGLang", "disaggregate prefill and decode for long-context workloads", "transfer KVCache between GPU nodes over RDMA", "speed up rollout data transfer in disaggregated reinforcement learning", "share KV cache across inference instances to avoid recomputation"], "what_it_is": "Mooncake is a KVCache-centric disaggregated serving platform for LLM inference, originally built to serve Kimi by Moonshot AI. It separates prefill and decode clusters, pools KVCache across CPU, DRAM, and SSD resources via RDMA, and includes a Transfer Engine and distributed Mooncake Store.", "when_to_avoid": ["you serve small models on a single GPU without RDMA hardware", "you need a simple turnkey inference server rather than serving infrastructure", "your deployment lacks high-speed networking between nodes"], "when_to_choose": ["you operate multi-node LLM inference at scale and need KVCache reuse", "you want prefill/decode disaggregation with vLLM, SGLang, or TRT-LLM", "you have RDMA-capable GPU clusters and long-context workloads", "you need a distributed cache backend for RL rollout or online training"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/mooncake", "repo": "kvcache-ai/Mooncake", "role": "main", "score": 91}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:43.056954+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:45:01.762004+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "371d31382c6683e84bdbe4713fb1a2662921dc4911347f1b6864d1784f21f15b", "fetched_at": "2026-08-28T04:09:43.056954+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kvcache-ai/Mooncake"}, {"content_hash": "3159b482bb6f6b9db4b04d1e4655198daaf77f9ac2af94b5ee978fd83353062a", "fetched_at": "2026-08-29T08:41:52.140606+00:00", "kind": "homepage", "missing": false, "url": "https://kvcache-ai.github.io/Mooncake/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:43.056954+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:45:01.762004+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "371d31382c6683e84bdbe4713fb1a2662921dc4911347f1b6864d1784f21f15b", "fetched_at": "2026-08-28T04:09:43.056954+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kvcache-ai/Mooncake"}, {"content_hash": "3159b482bb6f6b9db4b04d1e4655198daaf77f9ac2af94b5ee978fd83353062a", "fetched_at": "2026-08-29T08:41:52.140606+00:00", "kind": "homepage", "missing": false, "url": "https://kvcache-ai.github.io/Mooncake/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:45:01.762004+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "371d31382c6683e84bdbe4713fb1a2662921dc4911347f1b6864d1784f21f15b", "fetched_at": "2026-08-28T04:09:43.056954+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kvcache-ai/Mooncake"}, {"content_hash": "3159b482bb6f6b9db4b04d1e4655198daaf77f9ac2af94b5ee978fd83353062a", "fetched_at": "2026-08-29T08:41:52.140606+00:00", "kind": "homepage", "missing": false, "url": "https://kvcache-ai.github.io/Mooncake/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:43.056954+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:43.056954+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:43.056954+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:45:01.762004+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "371d31382c6683e84bdbe4713fb1a2662921dc4911347f1b6864d1784f21f15b", "fetched_at": "2026-08-28T04:09:43.056954+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kvcache-ai/Mooncake"}, {"content_hash": "3159b482bb6f6b9db4b04d1e4655198daaf77f9ac2af94b5ee978fd83353062a", "fetched_at": "2026-08-29T08:41:52.140606+00:00", "kind": "homepage", "missing": false, "url": "https://kvcache-ai.github.io/Mooncake/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:43.056954+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:43.056954+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:45:01.762004+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "371d31382c6683e84bdbe4713fb1a2662921dc4911347f1b6864d1784f21f15b", "fetched_at": "2026-08-28T04:09:43.056954+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kvcache-ai/Mooncake"}, {"content_hash": "3159b482bb6f6b9db4b04d1e4655198daaf77f9ac2af94b5ee978fd83353062a", "fetched_at": "2026-08-29T08:41:52.140606+00:00", "kind": "homepage", "missing": false, "url": "https://kvcache-ai.github.io/Mooncake/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:43.056954+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:43.056954+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:43.056954+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:45:01.762004+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "371d31382c6683e84bdbe4713fb1a2662921dc4911347f1b6864d1784f21f15b", "fetched_at": "2026-08-28T04:09:43.056954+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kvcache-ai/Mooncake"}, {"content_hash": "3159b482bb6f6b9db4b04d1e4655198daaf77f9ac2af94b5ee978fd83353062a", "fetched_at": "2026-08-29T08:41:52.140606+00:00", "kind": "homepage", "missing": false, "url": "https://kvcache-ai.github.io/Mooncake/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:43.056954+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:43.056954+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:45:01.762004+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "371d31382c6683e84bdbe4713fb1a2662921dc4911347f1b6864d1784f21f15b", "fetched_at": "2026-08-28T04:09:43.056954+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kvcache-ai/Mooncake"}, {"content_hash": "3159b482bb6f6b9db4b04d1e4655198daaf77f9ac2af94b5ee978fd83353062a", "fetched_at": "2026-08-29T08:41:52.140606+00:00", "kind": "homepage", "missing": false, "url": "https://kvcache-ai.github.io/Mooncake/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:45:01.762004+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "371d31382c6683e84bdbe4713fb1a2662921dc4911347f1b6864d1784f21f15b", "fetched_at": "2026-08-28T04:09:43.056954+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kvcache-ai/Mooncake"}, {"content_hash": "3159b482bb6f6b9db4b04d1e4655198daaf77f9ac2af94b5ee978fd83353062a", "fetched_at": "2026-08-29T08:41:52.140606+00:00", "kind": "homepage", "missing": false, "url": "https://kvcache-ai.github.io/Mooncake/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:45:01.762004+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "371d31382c6683e84bdbe4713fb1a2662921dc4911347f1b6864d1784f21f15b", "fetched_at": "2026-08-28T04:09:43.056954+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kvcache-ai/Mooncake"}, {"content_hash": "3159b482bb6f6b9db4b04d1e4655198daaf77f9ac2af94b5ee978fd83353062a", "fetched_at": "2026-08-29T08:41:52.140606+00:00", "kind": "homepage", "missing": false, "url": "https://kvcache-ai.github.io/Mooncake/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:45:01.762004+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "371d31382c6683e84bdbe4713fb1a2662921dc4911347f1b6864d1784f21f15b", "fetched_at": "2026-08-28T04:09:43.056954+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kvcache-ai/Mooncake"}, {"content_hash": "3159b482bb6f6b9db4b04d1e4655198daaf77f9ac2af94b5ee978fd83353062a", "fetched_at": "2026-08-29T08:41:52.140606+00:00", "kind": "homepage", "missing": false, "url": "https://kvcache-ai.github.io/Mooncake/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 57, "rhythm": 99}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 799, "days_push": 7, "days_rel": 7, "gap_med": 12, "n_releases_24m": 28}, "score": 91, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}