{"adoption": {"forks": 91, "observed_at": "2026-08-28T04:03:43.718387+00:00", "stars": 1136}, "canonical_url": "https://ross.abutalabs.com/products/marlin", "card": {"archived": false, "artifact_type": "library", "description": "FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.", "domain": ["large-language-models", "deep-learning", "gpu-computing"], "enriched": true, "function": ["llm-inference", "gpu-computing", "machine-learning"], "health_score": 20, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["IST-DASLab/marlin"], "name": "IST-DASLab/marlin", "platform": ["python"], "pushed_at": "2024-09-04T13:35:00+00:00", "repo": "IST-DASLab/marlin", "stars": 1136, "tags": ["quantization", "4bit-weights", "cuda-kernel", "matmul", "weight-only-quantization", "gpu", "linux"], "topics": ["4bit", "kernel", "llm", "quantization"], "urls": [], "use_cases": ["speed up LLM inference with 4-bit quantized weights", "serve quantized models at medium batch sizes", "accelerate speculative decoding", "run multi-inference schemes like CoT-Majority efficiently", "integrate a fast FP16xINT4 matmul kernel into inference frameworks"], "what_it_is": "Marlin is a highly optimized FP16xINT4 matrix multiplication CUDA kernel for LLM inference that achieves near-ideal 4x speedups at batch sizes up to 16-32 tokens. It uses advanced GPU optimization techniques to fully saturate memory, cache, and tensor core resources simultaneously.", "when_to_avoid": ["you need very large batch sizes where the kernel's advantage diminishes", "you need mixed FP16xINT4 support on non-NVIDIA or older GPUs", "you want a full inference engine rather than a single matmul kernel"], "when_to_choose": ["you need near-4x speedups from weight-only 4-bit quantization at batch sizes of 16-32 tokens", "you are serving quantized LLMs at larger scale or with speculative decoding", "prior kernels only give speedups at batch size 1-2 and you need more throughput"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/marlin", "repo": "IST-DASLab/marlin", "role": "main", "score": 26}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:43.718387+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:36:25.798814+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fca58d990c884ff97d117d0fe7e152e55eaf29216a091ce0ebe65caf843a0a6d", "fetched_at": "2026-08-28T04:03:43.718387+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IST-DASLab/marlin"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:43.718387+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:36:25.798814+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fca58d990c884ff97d117d0fe7e152e55eaf29216a091ce0ebe65caf843a0a6d", "fetched_at": "2026-08-28T04:03:43.718387+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IST-DASLab/marlin"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:36:25.798814+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fca58d990c884ff97d117d0fe7e152e55eaf29216a091ce0ebe65caf843a0a6d", "fetched_at": "2026-08-28T04:03:43.718387+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IST-DASLab/marlin"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:43.718387+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:43.718387+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:43.718387+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:36:25.798814+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fca58d990c884ff97d117d0fe7e152e55eaf29216a091ce0ebe65caf843a0a6d", "fetched_at": "2026-08-28T04:03:43.718387+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IST-DASLab/marlin"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:43.718387+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:43.718387+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:36:25.798814+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fca58d990c884ff97d117d0fe7e152e55eaf29216a091ce0ebe65caf843a0a6d", "fetched_at": "2026-08-28T04:03:43.718387+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IST-DASLab/marlin"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:43.718387+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:43.718387+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:43.718387+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:36:25.798814+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fca58d990c884ff97d117d0fe7e152e55eaf29216a091ce0ebe65caf843a0a6d", "fetched_at": "2026-08-28T04:03:43.718387+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IST-DASLab/marlin"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:43.718387+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:43.718387+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:36:25.798814+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fca58d990c884ff97d117d0fe7e152e55eaf29216a091ce0ebe65caf843a0a6d", "fetched_at": "2026-08-28T04:03:43.718387+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IST-DASLab/marlin"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:36:25.798814+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fca58d990c884ff97d117d0fe7e152e55eaf29216a091ce0ebe65caf843a0a6d", "fetched_at": "2026-08-28T04:03:43.718387+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IST-DASLab/marlin"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:36:25.798814+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fca58d990c884ff97d117d0fe7e152e55eaf29216a091ce0ebe65caf843a0a6d", "fetched_at": "2026-08-28T04:03:43.718387+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IST-DASLab/marlin"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:36:25.798814+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fca58d990c884ff97d117d0fe7e152e55eaf29216a091ce0ebe65caf843a0a6d", "fetched_at": "2026-08-28T04:03:43.718387+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IST-DASLab/marlin"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 68, "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": 959, "days_push": 728, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 26, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}