Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | CUDA Runtime | Google Cloud Functions | ExLlamaV2 |
|---|---|---|---|
| Score | B-65 | C59 | D47 |
| Type | Serverless | ||
| Execution | aot | hybrid | aot |
| Interface | sdk | platform | sdk |
| Cold Start | 100ms | 300ms | 1000ms |
| Memory | 500MB | 128MB | 300MB |
| Startup | 50ms | 50ms | 200ms |
| Isolation | hardware | container | process |
| Maturity | production | production | stable |
| Languages | C, C++, Python | Python, JavaScript, TypeScript, Go, Java, Ruby, PHP | Python, C++, CUDA |
| License | Proprietary | Proprietary | MIT |
| Links |