Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | Text Generation Inference | MLC LLM | vLLM |
|---|---|---|---|
| Score | F39 | F38 | F35 |
| Type | |||
| Execution | hybrid | aot | jit |
| Interface | api | sdk | api |
| Cold Start | 10000ms | 2000ms | 5000ms |
| Memory | 2000MB | 500MB | 2000MB |
| Startup | 5000ms | 500ms | 3000ms |
| Isolation | container | process | process |
| Maturity | production | stable | production |
| Languages | Rust, Python | Python, C++ | Python |
| License | Apache-2.0 | Apache-2.0 | Apache-2.0 |
| Links |