{"adoption": {"forks": 84, "observed_at": "2026-08-28T04:03:30.759389+00:00", "stars": 1081}, "canonical_url": "https://ross.abutalabs.com/products/tiny-vllm", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM", "domain": ["large-language-models", "deep-learning", "gpu-computing", "tutorials"], "enriched": true, "function": ["llm-inference", "gpu-computing", "machine-learning"], "health_score": 79, "homepage": null, "language": "C++", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["jmaczan/tiny-vllm"], "name": "jmaczan/tiny-vllm", "platform": ["cpp"], "pushed_at": "2026-08-23T14:20:13+00:00", "repo": "jmaczan/tiny-vllm", "stars": 1081, "tags": ["cuda-kernels", "paged-attention", "kv-cache", "continuous-batching", "flashattention", "inference-engine", "course", "gpu", "linux"], "topics": ["ai", "hpc", "llm", "llm-inference", "vllm", "tiny-vllm", "cpp", "cuda", "pagedattention", "attention", "batching", "course", "inference"], "urls": [], "use_cases": ["learn how LLM inference engines work internally", "build a mini vLLM in C++ and CUDA", "understand PagedAttention and KV cache implementation", "study CUDA kernel engineering for transformers", "teach a university course on LLM inference systems", "implement continuous batching from scratch"], "what_it_is": "tiny-vllm is both a minimal high-performance LLM inference engine written in C++ and CUDA, and a hands-on course that walks through building it from scratch. It implements a Llama 3.2 1B forward pass with CUDA kernels, KV cache, continuous batching, FlashAttention-style online softmax, and PagedAttention.", "when_to_avoid": ["you need a production-ready inference server for real workloads", "you want broad model support beyond Llama-style architectures", "you prefer not to write or maintain CUDA code"], "when_to_choose": ["you want to learn inference engine internals by implementing them yourself", "you need a small readable codebase demonstrating PagedAttention and batching", "you are an educator looking for a teaching resource on GPU inference"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/tiny-vllm", "repo": "jmaczan/tiny-vllm", "role": "main", "score": 60}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.759389+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:51:22.843020+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "55901a8aa1460105887b61b1581e522b94ea92e01ec5c69b3174047e858f7a76", "fetched_at": "2026-08-28T04:03:30.759389+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jmaczan/tiny-vllm"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.759389+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:51:22.843020+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "55901a8aa1460105887b61b1581e522b94ea92e01ec5c69b3174047e858f7a76", "fetched_at": "2026-08-28T04:03:30.759389+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jmaczan/tiny-vllm"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:51:22.843020+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "55901a8aa1460105887b61b1581e522b94ea92e01ec5c69b3174047e858f7a76", "fetched_at": "2026-08-28T04:03:30.759389+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jmaczan/tiny-vllm"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.759389+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.759389+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.759389+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:51:22.843020+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "55901a8aa1460105887b61b1581e522b94ea92e01ec5c69b3174047e858f7a76", "fetched_at": "2026-08-28T04:03:30.759389+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jmaczan/tiny-vllm"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.759389+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.759389+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:51:22.843020+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "55901a8aa1460105887b61b1581e522b94ea92e01ec5c69b3174047e858f7a76", "fetched_at": "2026-08-28T04:03:30.759389+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jmaczan/tiny-vllm"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.759389+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.759389+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.759389+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:51:22.843020+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "55901a8aa1460105887b61b1581e522b94ea92e01ec5c69b3174047e858f7a76", "fetched_at": "2026-08-28T04:03:30.759389+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jmaczan/tiny-vllm"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.759389+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:30.759389+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:51:22.843020+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "55901a8aa1460105887b61b1581e522b94ea92e01ec5c69b3174047e858f7a76", "fetched_at": "2026-08-28T04:03:30.759389+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jmaczan/tiny-vllm"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:51:22.843020+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "55901a8aa1460105887b61b1581e522b94ea92e01ec5c69b3174047e858f7a76", "fetched_at": "2026-08-28T04:03:30.759389+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jmaczan/tiny-vllm"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:51:22.843020+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "55901a8aa1460105887b61b1581e522b94ea92e01ec5c69b3174047e858f7a76", "fetched_at": "2026-08-28T04:03:30.759389+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jmaczan/tiny-vllm"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:51:22.843020+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "55901a8aa1460105887b61b1581e522b94ea92e01ec5c69b3174047e858f7a76", "fetched_at": "2026-08-28T04:03:30.759389+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jmaczan/tiny-vllm"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 14, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 205, "days_push": 10, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 60, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}