{
 "repo": "ZinYY/AdaFlash",
 "url": "https://github.com/ZinYY/AdaFlash",
 "what": "AdaFlash is an open-source framework for faster speculative decoding that pairs Qwen3 target models with on-policy distilled diffusion drafters and an adaptive length head, served through a patched SGLang.",
 "language": "Python",
 "stars": null,
 "gain": null,
 "created": "",
 "uc_n": 3,
 "title": "Ada Flash",
 "show": true,
 "what_source": "deduped",
 "use_cases": "https://dedupedai.com/use-cases/zinyy-adaflash/",
 "use_cases_json": "https://dedupedai.com/use-cases/r/zinyy-adaflash.json",
 "json": "https://dedupedai.com/repos/r/zinyy-adaflash.json",
 "slug": "zinyy-adaflash",
 "api": "https://dedupedai.com/api/v1/repos/zinyy-adaflash.json",
 "api_version": "v1"
}