OpenScience logo
OpenScience template

vLLM Inference Lab: p99 Bench

OpenScience lab for OpenAI-compatible inference: design a vLLM-style serve stack, bench it, read real p50/p99. BYOK Anthropic plus optional HF token.

NewNew10.7 KB snapshotPro VM

What's inside

Harness

OpenScience

Plan

Pro

vCPU

2

Memory

6 GiB

Snapshot

10.7 KB

Setup prompt + walkthrough

The vLLM Inference Lab: p99 Bench setup prompt + walkthrough

Paste this into any capable agent and it walks you through the connections, the trigger, and a supervised first run — the whole setup, in your own words. Or skip the setup and run this exact agent hosted.

Set up an agent for me, in its own chat, that does the work of a vLLM Inference Lab: p99 Bench. Work from the files and facts I actually give it, rank what matters by impact rather than by how many items it found, and stop short of sending, filing, posting, or changing anything live unless I ask for that in the same run. Walk me through connecting Anthropic, Gemini, Hugging Face, OpenAI, and OpenRouter. Have it run whenever I hand it the work, and every weekday morning on whatever I left unfinished. Ask me where the source material lives, who should receive the output, and what good enough looks like for a first pass. Run one pass while I watch, then save it.

Already built, running in ~3 min · 30-day money-back on first purchase

How it works · ~3 minutes

  1. 01 · Fork

    New isolated microVM on your subdomain — creator agent state included.

  2. 02 · Your keys

    Log into OpenScience with your own model credentials (BYOK).

  3. 03 · Ask it to work

    Open the terminal and give the agent a real job. You keep what ships.

Example first ask

Pull my open PRs, summarize risk, and draft a review checklist.

30-day money-back on your first purchase · no free trial · keys never leave the VM

About this template

Serve a model. Measure it. Stop guessing at latency.

If you need an OpenAI-compatible serve shape and honest p50/p99 numbers — not a screenshot of somebody else's benchmark — this OpenScience lab is already laid out for serve and bench work.

Numbers, written to disk.

What the vLLM-style serve and bench loop covers

Two skills, one workflow.

ml-inference-serve designs the serving stack: the OpenAI-compatible endpoint shape, the client config, the runbook. ml-inference-bench measures it — latency and throughput, reported as p50 and p99 instead of "feels fast." Results land under a fixed layout, which is what makes two runs comparable a week apart.

Design first. Then measure.

Worth saying up front: the fork ships those two skills and the directory layout, not a running server. ml-inference-serve designs the stack — installing vLLM, or whatever you serve with, is still your step.

What lands in your fork

  • The OpenScience ml agent as the default for inference work
  • ml-inference-serve — designs inference serving stacks
  • ml-inference-bench — latency and throughput benches
  • Layout: ~/ml-inference-lab/{serve,bench,clients,runbooks}/

What you supply (BYOK)

A model key, plus a Hugging Face token if you pull weights.

export ANTHROPIC_API_KEY=sk-ant-...
# export HF_TOKEN=...   # optional, for Hugging Face pulls

OPENAI_API_KEY, GEMINI_API_KEY and OPENROUTER_API_KEY are read too. Keys never ship in the snapshot.

Your first five minutes

Fork, then click Open OpenScience.

Ask the ml agent for the whole thing at once:

Serve this model with an OpenAI-compatible API and run a latency/throughput bench. Report p50 and p99.

You should land configs and results under the lab layout — a file you can diff next month, not a wall of unmeasured advice.

Honest limits

Read this part before you fork.

No GPU is attached to the VM, so you bench the endpoints and hardware you point it at, and GPU cost stays yours if you attach any. This is a lab on your own VM, not a managed multi-region inference product. If what you want is literature review and experiment scaffolding, take the ML co-scientist OpenScience template instead.

30-day money-back on your first jurniti purchase.

Fork it. Serve. Bench. Read the numbers.

Inside this fork

Forking copies this template into a brand-new, fully isolated microVM on your own subdomain. Here's exactly what lands in it.

  • OpenScience agent

    The upstream harness, pre-installed — same version the creator ran.

  • Pro VM

    2 vCPU · 6 GiB RAM · 50 GiB disk.

  • Creator's /persist data

    The captured persist volume is copied byte-for-byte into your fork.

  • BYOK — your keys, your VM

    Add your model API keys after forking; they live only inside your microVM.

What this agent can do

2 skills

  • ml-inference-bench

    Latency/throughput benches

  • ml-inference-serve

    Design inference serving stacks

What you'll configure after forking

Secrets are scrubbed from shared templates — these are the names you supply in your agent's terminal once it boots.

Environment variables

  • ANTHROPIC_API_KEY
  • GEMINI_API_KEY
  • HF_TOKEN
  • OPENAI_API_KEY
  • OPENROUTER_API_KEY

Your turn

Your own vLLM Inference Lab: p99 Bench, live in about 3 minutes.

Copy the setup prompt and build it yourself — or let this exact OpenScienceagent run hosted, already built, on a brand-new, fully isolated microVM on your own subdomain. Add your own keys after it boots; they never leave the box. Don't love it? Your first jurniti purchase comes with 30 days to get every cent back.

New paid VM · BYOK · 30-day money-back on your first purchase · ~3 min to provision

Needs 5 of your own API keys