RunInfraby RightNow

Pricing
Research
Contact

Dashboard Sign in Get started

Engines

Measured serving engines for open model inference

The published evidence currently covers 3 engines and 4 published packages.

SGLang
0 published packages
Comparison scope
Llama 3.1 8B Instruct on NVIDIA H100 80GB and NVIDIA L40S 48GB, measured Jun 20, 2026.
Measured versions
0.5.13
Evidence sources
Comparison rows and published package records stay separated on the detail page.
TensorRT-LLM
0 published packages
Comparison scope
Llama 3.1 8B Instruct on NVIDIA H100 80GB and NVIDIA L40S 48GB, measured Jun 20, 2026.
Measured versions
1.2.1
Evidence sources
Comparison rows and published package records stay separated on the detail page.
vLLM
4 published packages
Comparison scope
Llama 3.1 8B Instruct on NVIDIA H100 80GB and NVIDIA L40S 48GB, measured Jun 20, 2026.
Measured versions
0.23.0, 0.23.1, and 0.25.1
Evidence sources
Comparison rows and published package records stay separated on the detail page.

RunInfraby RightNow

© 2026 RunInfra. All rights reserved.

Pipeline Builder Model APIs Cost Calculator Pricing Startups Benchmarks Docs Research News Contact

Backed by

Combinator

NVIDIA Inception Program

Ask AI about RunInfra

Part of RightNow

Security DPA AUP Cookies Terms Privacy