Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | Python (CPython) | CTransformers | Text Generation Inference | vLLM |
|---|---|---|---|---|
| Score | B71 | D46 | F39 | F35 |
| Type | Language | |||
| Execution | interpreted | hybrid | hybrid | jit |
| Interface | cli | sdk | api | api |
| Cold Start | 50ms | 800ms | 10000ms | 5000ms |
| Memory | 15MB | 200MB | 2000MB | 2000MB |
| Startup | 10ms | 100ms | 5000ms | 3000ms |
| Isolation | process | process | container | process |
| Maturity | production | stable | production | production |
| Languages | Python | Python, C++ | Rust, Python | Python |
| License | Other | MIT | Apache-2.0 | Apache-2.0 |
| Links |