InferHub

Open vLLM and SGLang inference benchmarks, contributed by the community.
Server Launch Configs →
Checking sign-in…
loading...

Add a benchmark result

Paste or upload your benchmark output. Use the CLI skill instead →
Server launch command
Optional, you can modify this via Edit.
Benchmark launch command
Optional, you can modify this via Edit.
Benchmark result (REQUIRED)
Hardware info RECOMMENDED
Run this one-liner on your GPU machine to collect hardware info automatically.
Waiting for hardware data...
Why this run? (optional)

Browse and compare runs

Best throughput (tok/s)
-
tok/s
Lowest mean TTFT
-
ms
Lowest mean TPOT
-
ms

Benchmark library - means data was missing or could not be parsed.

Folded groups similar deployment variants into a single row. Click Expanded to see every run individually.
Engine Source HF model GPUs I/O len Throughput (tok/s) Mean TTFT (ms) Mean TPOT (ms) Actions Details