Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | gVisor | Python (CPython) | llama.cpp | Text Generation Inference |
|---|---|---|---|---|
| Score | B72 | B71 | C+63 | F39 |
| Type | MicroVM | Language | ||
| Execution | hybrid | interpreted | aot | hybrid |
| Interface | cli | cli | cli | api |
| Cold Start | 50ms | 50ms | 100ms | 10000ms |
| Memory | 20MB | 15MB | 50MB | 2000MB |
| Startup | 30ms | 10ms | 10ms | 5000ms |
| Isolation | microvm | process | process | container |
| Maturity | stable | production | production | production |
| Languages | Any | Python | C, C++ | Rust, Python |
| License | Apache-2.0 | Other | MIT | Apache-2.0 |
| Links |