norohind/ollama
1
0
Fork 0
forked from third-party-mirrors/ollama
Code Pull Requests Activity

Remove mem check

Browse Source
This commit is contained in:
norohind 2024-11-14 13:26:13 +01:00
parent 67691e410d
commit 1401b24c79
Signed by: norohind
SSH Key Fingerprint: SHA256:SnI4bWnejM2/YEQ5hpH58TUohiQpnjoKN6tXUQlobE0
1 changed files with 0 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
llm/server.go
View File

@ -128,17 +128,6 @@ func NewLlamaServer(gpus discover.GpuInfoList, model string, ggml *GGML, adapter
}
}
// On linux and windows, over-allocating CPU memory will almost always result in an error
// Darwin has fully dynamic swap so has no direct concept of free swap space
if runtime.GOOS != "darwin" {
systemMemoryRequired := estimate.TotalSize - estimate.VRAMSize
available := systemFreeMemory + systemSwapFreeMemory
if systemMemoryRequired > available {
slog.Warn("model request too large for system", "requested", format.HumanBytes2(systemMemoryRequired), "available", available, "total", format.HumanBytes2(systemTotalMemory), "free", format.HumanBytes2(systemFreeMemory), "swap", format.HumanBytes2(systemSwapFreeMemory))
return nil, fmt.Errorf("model requires more system memory (%s) than is available (%s)", format.HumanBytes2(systemMemoryRequired), format.HumanBytes2(available))
}
}
estimate.log()
// Loop through potential servers