Select runtimes to compare side by side. Click chips below to toggle selection.
| Metric | CUDA Runtime | llama.cpp | Google Cloud Functions |
|---|---|---|---|
| Score | B-65 | C+63 | C59 |
| Type | Serverless | ||
| Execution | aot | aot | hybrid |
| Interface | sdk | cli | platform |
| Cold Start | 100ms | 100ms | 300ms |
| Memory | 500MB | 50MB | 128MB |
| Startup | 50ms | 10ms | 50ms |
| Isolation | hardware | process | container |
| Maturity | production | production | production |
| Languages | C, C++, Python | C, C++ | Python, JavaScript, TypeScript, Go, Java, Ruby, PHP |
| License | Proprietary | MIT | Proprietary |
| Links |