Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | CUDA Runtime | Text Generation Inference | Jan |
|---|---|---|---|
| Score | B-65 | F39 | F34 |
| Type | |||
| Execution | aot | hybrid | hybrid |
| Interface | sdk | api | gui |
| Cold Start | 100ms | 10000ms | 2000ms |
| Memory | 500MB | 2000MB | 600MB |
| Startup | 50ms | 5000ms | 400ms |
| Isolation | hardware | container | process |
| Maturity | production | production | stable |
| Languages | C, C++, Python | Rust, Python | TypeScript, Python |
| License | Proprietary | Apache-2.0 | AGPL-3.0 |
| Links |