{"adoption": {"forks": 591, "observed_at": "2026-08-28T04:10:30.789390+00:00", "stars": 9352}, "canonical_url": "https://ross.abutalabs.com/products/flexllmgen", "card": {"archived": true, "artifact_type": "library", "description": "Running large language models on a single GPU for throughput-oriented scenarios.", "domain": ["large-language-models", "deep-learning", "machine-learning"], "enriched": true, "function": ["llm-inference", "machine-learning", "gpu-computing"], "health_score": 10, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["FMInference/FlexLLMGen"], "name": "FMInference/FlexLLMGen", "platform": ["python"], "pushed_at": "2024-10-28T03:05:41+00:00", "repo": "FMInference/FlexLLMGen", "stars": 9352, "tags": ["offloading", "high-throughput", "single-gpu", "model-compression", "batch-inference", "gpu", "linux"], "topics": ["deep-learning", "gpt-3", "high-throughput", "large-language-models", "machine-learning", "offloading", "opt"], "urls": [], "use_cases": ["run large language model inference on a single consumer GPU", "classify or extract information from millions of documents in batches", "benchmark LLMs like HELM on limited hardware", "process a company's private document corpus with an LLM overnight", "run OPT or GPT-style models with limited GPU memory", "reduce inference costs by trading latency for throughput"], "what_it_is": "FlexLLMGen is a high-throughput generation engine for running large language models on a single GPU with limited memory. It uses IO-efficient offloading, compression, and large effective batch sizes to maximize tokens-per-second for throughput-oriented batch inference workloads.", "when_to_avoid": ["you need low-latency interactive chat responses", "you have enough powerful GPUs to hold the whole model in memory", "you need small-batch or real-time inference"], "when_to_choose": ["you need to process large batches of text and throughput matters more than latency", "you only have a single commodity GPU but want to run large models", "you are running offline batch jobs like data wrangling or benchmarking"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/flexllmgen", "repo": "FMInference/FlexLLMGen", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:30.789390+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:22:26.739182+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "866f38aaf8b59a91bda14fab2d7121eaf75cec3b0fc210b072243fb35d4c6481", "fetched_at": "2026-08-28T04:10:30.789390+00:00", "kind": "readme", "missing": false, "url": "https://github.com/FMInference/FlexLLMGen"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:30.789390+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:22:26.739182+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "866f38aaf8b59a91bda14fab2d7121eaf75cec3b0fc210b072243fb35d4c6481", "fetched_at": "2026-08-28T04:10:30.789390+00:00", "kind": "readme", "missing": false, "url": "https://github.com/FMInference/FlexLLMGen"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:22:26.739182+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "866f38aaf8b59a91bda14fab2d7121eaf75cec3b0fc210b072243fb35d4c6481", "fetched_at": "2026-08-28T04:10:30.789390+00:00", "kind": "readme", "missing": false, "url": "https://github.com/FMInference/FlexLLMGen"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:30.789390+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:30.789390+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:30.789390+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:22:26.739182+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "866f38aaf8b59a91bda14fab2d7121eaf75cec3b0fc210b072243fb35d4c6481", "fetched_at": "2026-08-28T04:10:30.789390+00:00", "kind": "readme", "missing": false, "url": "https://github.com/FMInference/FlexLLMGen"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:30.789390+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:30.789390+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:22:26.739182+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "866f38aaf8b59a91bda14fab2d7121eaf75cec3b0fc210b072243fb35d4c6481", "fetched_at": "2026-08-28T04:10:30.789390+00:00", "kind": "readme", "missing": false, "url": "https://github.com/FMInference/FlexLLMGen"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:30.789390+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:30.789390+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:30.789390+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:22:26.739182+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "866f38aaf8b59a91bda14fab2d7121eaf75cec3b0fc210b072243fb35d4c6481", "fetched_at": "2026-08-28T04:10:30.789390+00:00", "kind": "readme", "missing": false, "url": "https://github.com/FMInference/FlexLLMGen"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:30.789390+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:30.789390+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:22:26.739182+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "866f38aaf8b59a91bda14fab2d7121eaf75cec3b0fc210b072243fb35d4c6481", "fetched_at": "2026-08-28T04:10:30.789390+00:00", "kind": "readme", "missing": false, "url": "https://github.com/FMInference/FlexLLMGen"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:22:26.739182+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "866f38aaf8b59a91bda14fab2d7121eaf75cec3b0fc210b072243fb35d4c6481", "fetched_at": "2026-08-28T04:10:30.789390+00:00", "kind": "readme", "missing": false, "url": "https://github.com/FMInference/FlexLLMGen"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:22:26.739182+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "866f38aaf8b59a91bda14fab2d7121eaf75cec3b0fc210b072243fb35d4c6481", "fetched_at": "2026-08-28T04:10:30.789390+00:00", "kind": "readme", "missing": false, "url": "https://github.com/FMInference/FlexLLMGen"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:22:26.739182+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "866f38aaf8b59a91bda14fab2d7121eaf75cec3b0fc210b072243fb35d4c6481", "fetched_at": "2026-08-28T04:10:30.789390+00:00", "kind": "readme", "missing": false, "url": "https://github.com/FMInference/FlexLLMGen"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 92, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1295, "days_push": 674, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}