Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | CUDA Runtime | Podman | Text Generation Inference |
|---|---|---|---|
| Score | B-65 | C57 | F39 |
| Type | Container | ||
| Execution | aot | hybrid | hybrid |
| Interface | sdk | cli | api |
| Cold Start | 100ms | 200ms | 10000ms |
| Memory | 500MB | 50MB | 2000MB |
| Startup | 50ms | 100ms | 5000ms |
| Isolation | hardware | container | container |
| Maturity | production | stable | production |
| Languages | C, C++, Python | Any | Rust, Python |
| License | Proprietary | Apache-2.0 | Apache-2.0 |
| Links |