{"adoption": {"forks": 309, "observed_at": "2026-08-28T04:07:58.441984+00:00", "stars": 3374}, "canonical_url": "https://ross.abutalabs.com/products/roll", "card": {"archived": false, "artifact_type": "library", "description": "An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models", "domain": ["large-language-models", "reinforcement-learning", "machine-learning", "gpu-computing"], "enriched": true, "function": ["llm-training", "reinforcement-learning", "llm-inference", "agent-framework", "gpu-computing"], "health_score": 99, "homepage": "https://alibaba.github.io/ROLL/", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["alibaba/ROLL"], "name": "alibaba/ROLL", "platform": ["python", "cloud"], "pushed_at": "2026-08-26T01:34:48+00:00", "repo": "alibaba/ROLL", "stars": 3374, "tags": ["rlhf", "rlvr", "ppo", "grpo", "ray", "vllm", "sglang", "megatron-core", "distributed-training", "agentic-rl", "ai-agents", "gpu", "linux", "docker"], "topics": ["agentic", "rlhf", "rlvr"], "urls": [], "use_cases": ["train an LLM with RLHF for human preference alignment", "run RLVR training to improve model reasoning", "fine-tune an LLM with PPO or GRPO on a GPU cluster", "train multi-turn agentic RL policies", "scale reinforcement learning post-training to thousands of GPUs", "on-policy distillation of large language models"], "what_it_is": "ROLL is an open-source reinforcement learning library from Alibaba for training large language models at scale, supporting algorithms like PPO and GRPO. It uses a Ray-based distributed architecture integrating Megatron-Core, SGLang, and vLLM for efficient training and inference across large GPU clusters.", "when_to_avoid": ["you only need simple supervised fine-tuning without reinforcement learning", "you lack access to substantial GPU resources", "you need a lightweight single-GPU RLHF tool with minimal setup"], "when_to_choose": ["you need large-scale RL post-training for LLMs with flexible multi-node GPU allocation", "you want built-in support for PPO, GRPO, multi-task RL, and agentic interaction scenarios", "you want to combine Megatron-Core training with vLLM/SGLang inference engines"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/roll", "repo": "alibaba/ROLL", "role": "main", "score": 78}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.441984+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:39:55.853826+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "be3c183a7a010001c5a53deea0c207f6917bde94c6230fa7b1d6ad923ccfec29", "fetched_at": "2026-08-28T04:07:58.441984+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alibaba/ROLL"}, {"content_hash": "db0bd3822ad2fc7e7a9e551a9e533e739ff084798d61ca7737283be5dd76ace7", "fetched_at": "2026-08-29T09:33:38.692482+00:00", "kind": "homepage", "missing": false, "url": "https://alibaba.github.io/ROLL/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.441984+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:39:55.853826+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "be3c183a7a010001c5a53deea0c207f6917bde94c6230fa7b1d6ad923ccfec29", "fetched_at": "2026-08-28T04:07:58.441984+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alibaba/ROLL"}, {"content_hash": "db0bd3822ad2fc7e7a9e551a9e533e739ff084798d61ca7737283be5dd76ace7", "fetched_at": "2026-08-29T09:33:38.692482+00:00", "kind": "homepage", "missing": false, "url": "https://alibaba.github.io/ROLL/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:39:55.853826+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "be3c183a7a010001c5a53deea0c207f6917bde94c6230fa7b1d6ad923ccfec29", "fetched_at": "2026-08-28T04:07:58.441984+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alibaba/ROLL"}, {"content_hash": "db0bd3822ad2fc7e7a9e551a9e533e739ff084798d61ca7737283be5dd76ace7", "fetched_at": "2026-08-29T09:33:38.692482+00:00", "kind": "homepage", "missing": false, "url": "https://alibaba.github.io/ROLL/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.441984+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.441984+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.441984+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:39:55.853826+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "be3c183a7a010001c5a53deea0c207f6917bde94c6230fa7b1d6ad923ccfec29", "fetched_at": "2026-08-28T04:07:58.441984+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alibaba/ROLL"}, {"content_hash": "db0bd3822ad2fc7e7a9e551a9e533e739ff084798d61ca7737283be5dd76ace7", "fetched_at": "2026-08-29T09:33:38.692482+00:00", "kind": "homepage", "missing": false, "url": "https://alibaba.github.io/ROLL/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.441984+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.441984+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:39:55.853826+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "be3c183a7a010001c5a53deea0c207f6917bde94c6230fa7b1d6ad923ccfec29", "fetched_at": "2026-08-28T04:07:58.441984+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alibaba/ROLL"}, {"content_hash": "db0bd3822ad2fc7e7a9e551a9e533e739ff084798d61ca7737283be5dd76ace7", "fetched_at": "2026-08-29T09:33:38.692482+00:00", "kind": "homepage", "missing": false, "url": "https://alibaba.github.io/ROLL/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.441984+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.441984+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.441984+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:39:55.853826+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "be3c183a7a010001c5a53deea0c207f6917bde94c6230fa7b1d6ad923ccfec29", "fetched_at": "2026-08-28T04:07:58.441984+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alibaba/ROLL"}, {"content_hash": "db0bd3822ad2fc7e7a9e551a9e533e739ff084798d61ca7737283be5dd76ace7", "fetched_at": "2026-08-29T09:33:38.692482+00:00", "kind": "homepage", "missing": false, "url": "https://alibaba.github.io/ROLL/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.441984+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.441984+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:39:55.853826+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "be3c183a7a010001c5a53deea0c207f6917bde94c6230fa7b1d6ad923ccfec29", "fetched_at": "2026-08-28T04:07:58.441984+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alibaba/ROLL"}, {"content_hash": "db0bd3822ad2fc7e7a9e551a9e533e739ff084798d61ca7737283be5dd76ace7", "fetched_at": "2026-08-29T09:33:38.692482+00:00", "kind": "homepage", "missing": false, "url": "https://alibaba.github.io/ROLL/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:39:55.853826+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "be3c183a7a010001c5a53deea0c207f6917bde94c6230fa7b1d6ad923ccfec29", "fetched_at": "2026-08-28T04:07:58.441984+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alibaba/ROLL"}, {"content_hash": "db0bd3822ad2fc7e7a9e551a9e533e739ff084798d61ca7737283be5dd76ace7", "fetched_at": "2026-08-29T09:33:38.692482+00:00", "kind": "homepage", "missing": false, "url": "https://alibaba.github.io/ROLL/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:39:55.853826+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "be3c183a7a010001c5a53deea0c207f6917bde94c6230fa7b1d6ad923ccfec29", "fetched_at": "2026-08-28T04:07:58.441984+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alibaba/ROLL"}, {"content_hash": "db0bd3822ad2fc7e7a9e551a9e533e739ff084798d61ca7737283be5dd76ace7", "fetched_at": "2026-08-29T09:33:38.692482+00:00", "kind": "homepage", "missing": false, "url": "https://alibaba.github.io/ROLL/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:39:55.853826+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "be3c183a7a010001c5a53deea0c207f6917bde94c6230fa7b1d6ad923ccfec29", "fetched_at": "2026-08-28T04:07:58.441984+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alibaba/ROLL"}, {"content_hash": "db0bd3822ad2fc7e7a9e551a9e533e739ff084798d61ca7737283be5dd76ace7", "fetched_at": "2026-08-29T09:33:38.692482+00:00", "kind": "homepage", "missing": false, "url": "https://alibaba.github.io/ROLL/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 33, "rhythm": 77}, "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": 462, "days_push": 8, "days_rel": 76, "gap_med": 58, "n_releases_24m": 4}, "score": 78, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}