{
 "schema_version": 1,
 "generated": "2026-10-31",
 "id": "zinyy-adaflash--serve-qwen3-with-adaflash-drafter",
 "repo": "ZinYY/AdaFlash",
 "repo_url": "https://github.com/ZinYY/AdaFlash",
 "repo_slug": "zinyy-adaflash",
 "title": "Serve Qwen3-8B with an Ada Flash drafter and test it over HTTP",
 "page_title": "How to serve Qwen3-8B with an Ada Flash drafter and test it over HTTP with Ada Flash",
 "summary": "Launch an Ada Flash SGLang server for Qwen3-8B and send requests to its /generate endpoint.",
 "who": "A developer who runs a Qwen3-8B inference endpoint and wants lower latency from speculative decoding without changing the target model.",
 "problem": "Plain autoregressive decoding is slow for an internal Qwen3-8B service, and the team needs a tested way to swap in a faster drafter.",
 "outcome": "A running Ada Flash server for Qwen3-8B that answers requests on the /generate endpoint, with timings from the included benchmark client.",
 "steps": [
  "Complete the environment setup with `conda create -n adaflash python=3.12 -y`, `conda activate adaflash`, the patched SGLang install, and `pip install -r requirements.txt`.",
  "Launch the Ada Flash server with `scripts/serve/serve_thresh_head.sh`, which the README lists as the Ada Flash serving launcher.",
  "Wait until the server reports ready, then run `python bin/benchmark.py` against its `/generate` endpoint.",
  "Compare the output with the Vanilla launcher `scripts/serve/serve_sglang.sh` using the same benchmark client and settings."
 ],
 "agent_prompt": "In the ZinYY/AdaFlash repo, start the AdaFlash server with scripts/serve/serve_thresh_head.sh for Qwen/Qwen3-8B and then run python bin/benchmark.py against its /generate endpoint. Expected output is a benchmark summary from the client. Verify that the server is ready before sending requests and that the drafter is AdaFlash/Qwen3-8B-PerfectBlend.",
 "agents": [
  "any"
 ],
 "difficulty": "Intermediate",
 "time": "1 hour 15 minutes",
 "basis": "readme",
 "caveat": "The README does not document the serve script arguments, so check the script header or docs before changing its defaults for your model or GPUs.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "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"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.9,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/zinyy-adaflash/serve-qwen3-with-adaflash-drafter/",
 "md": "https://dedupedai.com/use-cases/zinyy-adaflash/serve-qwen3-with-adaflash-drafter/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/zinyy-adaflash--serve-qwen3-with-adaflash-drafter.json",
 "api_version": "v1"
}