{
 "schema_version": 1,
 "generated": "2026-10-31",
 "repo": "ZinYY/AdaFlash",
 "name": "AdaFlash",
 "owner": "ZinYY",
 "slug": "zinyy-adaflash",
 "github": "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.",
 "why": "133 stars, launched 81 days ago",
 "language": "Python",
 "requirements": [
  "A Linux machine with NVIDIA GPUs and CUDA, since the README sets CUDA devices and separate GPU sets for serving and training",
  "Conda and Python 3.12, as used in the README install steps",
  "Access to the Qwen3-8B target model and the AdaFlash/DFlash checkpoints on Hugging Face",
  "The patched SGLang version from the linked SGLang PR, because a stock SGLang release may not expose the required arguments"
 ],
 "audience_note": "Built for ML engineers and researchers who serve or train Qwen3-family models and want to measure or improve speculative decoding speed.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Software and DevOps",
 "url": "https://dedupedai.com/use-cases/zinyy-adaflash/",
 "use_case_count": 3,
 "use_cases": [
  {
   "id": "zinyy-adaflash--benchmark-adaflash-speedup-on-gsm8k",
   "title": "Measure Ada Flash decoding speed against baselines on GSM8K",
   "best": true,
   "url": "https://dedupedai.com/use-cases/zinyy-adaflash/benchmark-adaflash-speedup-on-gsm8k/",
   "json": "https://dedupedai.com/use-cases/u/zinyy-adaflash/benchmark-adaflash-speedup-on-gsm8k.json"
  },
  {
   "id": "zinyy-adaflash--serve-qwen3-with-adaflash-drafter",
   "title": "Serve Qwen3-8B with an Ada Flash drafter and test it over HTTP",
   "best": false,
   "url": "https://dedupedai.com/use-cases/zinyy-adaflash/serve-qwen3-with-adaflash-drafter/",
   "json": "https://dedupedai.com/use-cases/u/zinyy-adaflash/serve-qwen3-with-adaflash-drafter.json"
  },
  {
   "id": "zinyy-adaflash--train-custom-adaflash-drafter",
   "title": "Train an Ada Flash drafter on your own response data",
   "best": false,
   "url": "https://dedupedai.com/use-cases/zinyy-adaflash/train-custom-adaflash-drafter/",
   "json": "https://dedupedai.com/use-cases/u/zinyy-adaflash/train-custom-adaflash-drafter.json"
  }
 ],
 "disclaimer": "Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk."
}