Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | ExLlamaV2 | Text Generation Inference | vLLM |
|---|---|---|---|
| Score | D47 | F39 | F35 |
| Type | |||
| Execution | aot | hybrid | jit |
| Interface | sdk | api | api |
| Cold Start | 1000ms | 10000ms | 5000ms |
| Memory | 300MB | 2000MB | 2000MB |
| Startup | 200ms | 5000ms | 3000ms |
| Isolation | process | container | process |
| Maturity | stable | production | production |
| Languages | Python, C++, CUDA | Rust, Python | Python |
| License | MIT | Apache-2.0 | Apache-2.0 |
| Links |