{"data":{"slug":"fasterdecoding-rest","name":"REST","tagline":"REST: Retrieval-Based Speculative Decoding","github_url":"https://github.com/FasterDecoding/REST","owner":"FasterDecoding","repo":"REST","owner_avatar_url":"https://avatars.githubusercontent.com/u/144572371?v=4","primary_language":"C","stars":220,"forks":17,"topics":["llm-inference","retrieval","speculative-decoding"],"archived":false,"github_pushed_at":"2026-03-05T12:38:16+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/fasterdecoding-rest","markdown_url":"https://www.graphcanon.com/tools/fasterdecoding-rest.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/fasterdecoding-rest","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=fasterdecoding-rest","description":"REST: Retrieval-Based Speculative Decoding, NAACL 2024","homepage_url":null,"license":"Apache-2.0","open_issues":15,"watchers":6,"ai_summary":"A tool for retrieval-based speculative decoding using the C programming language, introduced in NAACL 2024.","readme_excerpt":"## Installation\n```bash\nconda create -n rest python=3.9\nconda activate rest\npip3 install -r requirements.txt # pay attention to Pytorch CUDA version\npip3 install DraftRetriever/wheels/draftretriever-0.1.0-cp39-cp39-manylinux_2_34_x86_64.whl\n```","github_created_at":"2023-11-15T00:59:25+00:00","created_at":"2026-07-11T23:05:52.820039+00:00","updated_at":"2026-07-12T03:38:50.992036+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"llm-inference","name":"llm-inference"},{"slug":"retrieval","name":"retrieval"},{"slug":"speculative-decoding","name":"speculative-decoding"}],"trust":{"provenance":{"is_fork":false,"github_id":718875034,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T23:05:55.716Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":128,"last_release_at":null},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":2,"high_count":0,"last_scan_at":"2026-07-11T23:05:56.229Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-12T03:38:31.158Z"},"languages":{"value":["c"],"source":"github.language","observed_at":"2026-07-12T03:38:31.158Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-07-12T03:38:31.158Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["- When you need high performance and are willing to work with the C language for customization and optimization.","- If your project can benefit from retrieval-based speculative decoding, offering unique insights into model predictions based on past responses."],"when_not_to_use":["- Avoid if your team lacks proficiency in C programming as this may lead to an overhead in developing and maintaining the tool.","- Not recommended for projects where flexibility with commonly used high-level languages like Python is essential, as REST primarily relies on lower-level language capabilities."],"source":"enrich:decision_facts","observed_at":"2026-07-12T03:38:50.736Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"REST is a retrieval-based speculative decoding tool implemented in C, designed for use cases that demand efficiency and fine-grained control over inference processes through its distinctive approach."}]}}