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