gpu: add 512MiB to darwin minimum, metal doesn't have partial offloading overhead (#4068)

This commit is contained in:
Jeffrey Morgan 2024-05-01 11:46:03 -04:00 committed by GitHub
parent b9f74ff3d6
commit f0c454ab57
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 12 additions and 1 deletions

View file

@ -10,6 +10,12 @@ package gpu
import "C"
import (
"runtime"
"github.com/ollama/ollama/format"
)
const (
metalMinimumMemory = 512 * format.MebiByte
)
func GetGPUInfo() GpuInfoList {
@ -32,7 +38,7 @@ func GetGPUInfo() GpuInfoList {
// TODO is there a way to gather actual allocated video memory? (currentAllocatedSize doesn't work)
info.FreeMemory = info.TotalMemory
info.MinimumMemory = 0
info.MinimumMemory = metalMinimumMemory
return []GpuInfo{info}
}