{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "patchy631-time-to-first-token--compare-vllm-sglang-shared-prefix-workload",
 "repo": "patchy631/time-to-first-token",
 "repo_url": "https://github.com/patchy631/time-to-first-token",
 "repo_slug": "patchy631-time-to-first-token",
 "title": "Compare vLLM and SGLang on a shared-prefix workload",
 "page_title": "How to compare vLLM and SGLang on a shared-prefix workload with Time to First Token",
 "summary": "Run one model on both engines to measure the TTFT gap on prefix-heavy traffic.",
 "who": "ML engineer choosing a serving engine who needs evidence from a traffic pattern like their own.",
 "problem": "Engine performance claims depend on the workload, and the README points to prefix reuse as where RadixAttention helps.",
 "outcome": "A side-by-side TTFT and throughput comparison of vLLM and SGLang with pinned versions.",
 "steps": [
  "`pip install sglang`",
  "Deploy SGLang with the same model, prompt, and hardware used for the vLLM service, so the engine is the only variable.",
  "Run a workload with a shared system prompt against both engines.",
  "Record TTFT and throughput for each engine and note the versions used."
 ],
 "agent_prompt": "Using the patchy631/time-to-first-token repo, run the same model with a shared system prompt on vLLM and on SGLang at <GPU host>. Expected output: a table of TTFT and throughput for each engine. Verify that both runs used the same model, prompt set, and hardware before comparing numbers.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "4 hours",
 "basis": "readme",
 "caveat": "The README gives no benchmark numbers for this comparison, so results depend on your own model and hardware.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "html",
 "requirements": [
  "Python and command-line comfort",
  "One rented GPU with about 24GB of memory for a 7-8B model, billed by the half hour",
  "Docker for the Prometheus and Grafana stack",
  "An H100 for the 1000-concurrent load test in week 5"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.8,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/patchy631-time-to-first-token/compare-vllm-sglang-shared-prefix-workload/",
 "md": "https://dedupedai.com/use-cases/patchy631-time-to-first-token/compare-vllm-sglang-shared-prefix-workload/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/patchy631-time-to-first-token--compare-vllm-sglang-shared-prefix-workload.json",
 "api_version": "v1"
}