Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | Python (CPython) | LLM (Python CLI) | ExLlamaV2 | vLLM |
|---|---|---|---|---|
| Score | B71 | D49 | D47 | F35 |
| Type | Language | |||
| Execution | interpreted | hybrid | aot | jit |
| Interface | cli | cli | sdk | api |
| Cold Start | 50ms | 500ms | 1000ms | 5000ms |
| Memory | 15MB | 100MB | 300MB | 2000MB |
| Startup | 10ms | 100ms | 200ms | 3000ms |
| Isolation | process | process | process | process |
| Maturity | production | stable | stable | production |
| Languages | Python | Python | Python, C++, CUDA | Python |
| License | Other | Apache-2.0 | MIT | Apache-2.0 |
| Links |