highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-11-11 03:07:43 +01:00
Code Issues Packages Projects Releases Wiki Activity

llm: avoid loading model if system memory is too small (#5637)

Browse Source 
* llm: avoid loading model if system memory is too small

* update log

* Instrument swap free space

On linux and windows, expose how much swap space is available
so we can take that into consideration when scheduling models

* use `systemSwapFreeMemory` in check

---------

Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
This commit is contained in:
Jeffrey Morgan
2024-07-11 16:42:57 -07:00
committed by GitHub
parent 791650ddef
commit c4cf8ad559
6 changed files with 22 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
gpu/gpu_linux.go
View File

@@ -50,7 +50,7 @@ var OneapiMgmtName = "libze_intel_gpu.so"
func GetCPUMem() (memInfo, error) {
var mem memInfo
var total, available, free, buffers, cached uint64
var total, available, free, buffers, cached, freeSwap uint64
f, err := os.Open("/proc/meminfo")
if err != nil {
return mem, err
@@ -70,20 +70,21 @@ func GetCPUMem() (memInfo, error) {
_, err = fmt.Sscanf(line, "Buffers:%d", &buffers)
case strings.HasPrefix(line, "Cached:"):
_, err = fmt.Sscanf(line, "Cached:%d", &cached)
case strings.HasPrefix(line, "SwapFree:"):
_, err = fmt.Sscanf(line, "SwapFree:%d", &freeSwap)
default:
continue
}
if err != nil {
return mem, err
}
if total > 0 && available > 0 {
mem.TotalMemory = total * format.KibiByte
mem.FreeMemory = available * format.KibiByte
return mem, nil
}
}
mem.TotalMemory = total * format.KibiByte
mem.FreeMemory = (free + buffers + cached) * format.KibiByte
mem.FreeSwap = freeSwap * format.KibiByte
if available > 0 {
mem.FreeMemory = available * format.KibiByte
} else {
mem.FreeMemory = (free + buffers + cached) * format.KibiByte
}
return mem, nil
}