boltbeam.fyi

Make your inference engine faster, or you don't pay

  1. 1 Time
  2. 2 Setup
  3. 3 Confirm
November 2026
MoTuWeThFrSaSu

Pick a day to see times.

I make inference engines faster on your hardware: open-source engines like llama.cpp, vLLM and TensorRT-LLM, or your own closed-source one. You get a fixed quote with a speed target written in. If the target is not met, you pay nothing.

How it works

  1. You tell me the setup: engine, model, GPU, and the workload you care about (one user or many, short or long context).
  2. I measure it first, free. BoltBeam audits your setup against the roofline: the fastest your GPU can run that model. The gap is what can be won, and it tells both of us whether the job is worth doing.
  3. You get a fixed quote with one test in it. For example: decode at least 15% faster at batch 1 on your workload, measured by BoltBeam, before and after, paired runs on the same machine.
  4. I do the work. Engine patches, kernels, settings, or a lighter checkpoint, whichever closes the gap.
  5. The test decides. Same benchmark, same machine. If it passes, the quote is charged. If it does not, nothing is.

The guarantee

  • Card saved at $0 when you book. Nothing is charged for the audit.
  • Target met: the quoted amount is charged.
  • Target missed: nothing is charged, and you keep the audit.

Open or closed source

Open-source engines: the work can go upstream or stay as patches you own, your choice. Closed-source engines: fine, with your written permission to profile and modify the engine, under an NDA. The work runs on your hardware or a rented machine you approve, and the results stay private unless you want them published.

What I have shipped