Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | AWS Lambda | Text Generation Inference | KoboldCpp | vLLM |
|---|---|---|---|---|
| Score | B-65 | F39 | F38 | F35 |
| Type | Serverless | |||
| Execution | hybrid | hybrid | hybrid | jit |
| Interface | platform | api | gui | api |
| Cold Start | 200ms | 10000ms | 1500ms | 5000ms |
| Memory | 128MB | 2000MB | 400MB | 2000MB |
| Startup | 100ms | 5000ms | 300ms | 3000ms |
| Isolation | microvm | container | process | process |
| Maturity | production | production | stable | production |
| Languages | JavaScript, TypeScript, Python, Java, Go, Ruby, .NET, Rust | Rust, Python | C++, Python | Python |
| License | Proprietary | Apache-2.0 | AGPL-3.0 | Apache-2.0 |
| Links |