mirror of https://github.com/ollama/ollama.git
bd15eba4e4
* Bring back escape valve for llm libraries If the new discovery logic picks the wrong library, this gives users the ability to force a specific one using the same pattern as before. This can also potentially speed up bootstrap discovery if one of the libraries takes a long time to load and ultimately bind to no devices. For example unsupported AMD iGPUS can sometimes take a while to discover and rule out. * Bypass extra discovery on jetpack systems On at least Jetpack6, cuda_v12 appears to expose the iGPU, but crashes later on in cublasInit so if we detect a Jetpack, short-circuit and use that variant. |
||
|---|---|---|
| .. | ||
| cpu_linux.go | ||
| cpu_linux_test.go | ||
| cpu_windows.go | ||
| cpu_windows_test.go | ||
| gpu.go | ||
| gpu_darwin.go | ||
| gpu_info_darwin.h | ||
| gpu_info_darwin.m | ||
| path.go | ||
| runner.go | ||
| runner_test.go | ||
| types.go | ||