baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

llm: prevent loading too large models on windows (#5926)

Browse source 
Don't allow loading models that would lead to memory exhaustion (across vram, system memory and disk paging). This check was already applied on Linux but should also be applied on Windows as well.
This commit is contained in:
Daniel Hiltgen 2024-08-11 11:30:20 -07:00 committed by GitHub
parent 023451ce47
commit 25906d72d1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 3 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
llm/server.go
View file

@ -125,8 +125,9 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
}
}
// On linux, over-allocating CPU memory will almost always result in an error
if runtime.GOOS == "linux" {
// 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 {