{"adoption": {"forks": 80, "observed_at": "2026-08-28T04:04:15.706014+00:00", "stars": 1291}, "canonical_url": "https://ross.abutalabs.com/products/speculativedecodingpapers", "card": {"archived": false, "artifact_type": "learning-resource", "description": "📰 Must-read papers and blogs on Speculative Decoding ⚡️", "domain": ["large-language-models", "artificial-intelligence", "awesome-lists", "tutorials", "performance"], "enriched": true, "function": ["llm-inference", "machine-learning", "deep-learning", "nlp"], "health_score": 74, "homepage": null, "language": null, "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["hemingkx/SpeculativeDecodingPapers"], "name": "hemingkx/SpeculativeDecodingPapers", "platform": [], "pushed_at": "2026-06-27T00:21:39+00:00", "repo": "hemingkx/SpeculativeDecodingPapers", "stars": 1291, "tags": ["awesome-list", "speculative-decoding", "paper-list", "survey", "efficient-inference", "multi-token-prediction", "draft-models", "reading-list", "research", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["learn about speculative decoding for LLM inference", "find research papers on faster LLM token generation", "catch up on multi-token prediction and draft-model techniques", "prepare a related-work section on efficient LLM decoding", "find tutorials and blogs explaining speculative decoding", "track new publications on LLM inference acceleration"], "what_it_is": "A regularly updated curated reading list (awesome list) of must-read papers, blogs, and tutorials on speculative decoding for efficient large language model inference. It accompanies an ACL 2024 Findings survey and organizes research by drafting method, application area, and features such as multi-token prediction, MoE, and long-context decoding.", "when_to_avoid": ["you need runnable inference acceleration code or a serving library rather than a reading list", "you need production LLM serving or quantization tooling", "you need benchmark results you can run rather than references to benchmark papers"], "when_to_choose": ["you are starting research or a literature review on speculative decoding", "you need a curated, categorized, regularly updated bibliography with venue and method tags", "you want tutorials, slides, and blogs alongside academic papers"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/speculativedecodingpapers", "repo": "hemingkx/SpeculativeDecodingPapers", "role": "main", "score": 68}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.706014+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:54:47.257650+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "02460ac2fbdf5fcf5564c57b5109492fb5a6ea9e18f562a8e4e27d30037608bf", "fetched_at": "2026-08-28T04:04:15.706014+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hemingkx/SpeculativeDecodingPapers"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.706014+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:54:47.257650+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "02460ac2fbdf5fcf5564c57b5109492fb5a6ea9e18f562a8e4e27d30037608bf", "fetched_at": "2026-08-28T04:04:15.706014+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hemingkx/SpeculativeDecodingPapers"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:54:47.257650+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "02460ac2fbdf5fcf5564c57b5109492fb5a6ea9e18f562a8e4e27d30037608bf", "fetched_at": "2026-08-28T04:04:15.706014+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hemingkx/SpeculativeDecodingPapers"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.706014+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.706014+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.706014+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:54:47.257650+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "02460ac2fbdf5fcf5564c57b5109492fb5a6ea9e18f562a8e4e27d30037608bf", "fetched_at": "2026-08-28T04:04:15.706014+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hemingkx/SpeculativeDecodingPapers"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.706014+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.706014+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:54:47.257650+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "02460ac2fbdf5fcf5564c57b5109492fb5a6ea9e18f562a8e4e27d30037608bf", "fetched_at": "2026-08-28T04:04:15.706014+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hemingkx/SpeculativeDecodingPapers"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.706014+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.706014+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.706014+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:54:47.257650+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "02460ac2fbdf5fcf5564c57b5109492fb5a6ea9e18f562a8e4e27d30037608bf", "fetched_at": "2026-08-28T04:04:15.706014+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hemingkx/SpeculativeDecodingPapers"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.706014+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:15.706014+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:54:47.257650+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "02460ac2fbdf5fcf5564c57b5109492fb5a6ea9e18f562a8e4e27d30037608bf", "fetched_at": "2026-08-28T04:04:15.706014+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hemingkx/SpeculativeDecodingPapers"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:54:47.257650+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "02460ac2fbdf5fcf5564c57b5109492fb5a6ea9e18f562a8e4e27d30037608bf", "fetched_at": "2026-08-28T04:04:15.706014+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hemingkx/SpeculativeDecodingPapers"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:54:47.257650+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "02460ac2fbdf5fcf5564c57b5109492fb5a6ea9e18f562a8e4e27d30037608bf", "fetched_at": "2026-08-28T04:04:15.706014+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hemingkx/SpeculativeDecodingPapers"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:54:47.257650+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "02460ac2fbdf5fcf5564c57b5109492fb5a6ea9e18f562a8e4e27d30037608bf", "fetched_at": "2026-08-28T04:04:15.706014+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hemingkx/SpeculativeDecodingPapers"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 89, "longevity": 77, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1078, "days_push": 68, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 68, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}