pali112
/
ollama
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Applied 04-disable-mmap-vulkan.patch 

From: https://github.com/whyvl/ollama-vulkan/issues/7#issuecomment-2660836871

Signed-off-by: Vadim Grinco <vadim@grinco.eu>
This commit is contained in:
Vadim Grinco 2025-03-16 10:52:49 +01:00
parent f77b9b99cd
commit c2e440879a
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llm/server.go
View File

@ -207,10 +207,12 @@ func NewLlamaServer(gpus discover.GpuInfoList, modelPath string, f *ggml.GGML, a
}
// Windows CUDA should not use mmap for best performance
// Vulkan should not use mmap because of double allocation (VRAM + RAM)
// Linux with a model larger than free space, mmap leads to thrashing
// For CPU loads we want the memory to be allocated, not FS cache
if (runtime.GOOS == "windows" && gpus[0].Library == "cuda" && opts.UseMMap == nil) ||
(runtime.GOOS == "linux" && systemFreeMemory < estimate.TotalSize && opts.UseMMap == nil) ||
(gpus[0].Library == "vulkan" && opts.UseMMap == nil) ||
(gpus[0].Library == "cpu" && opts.UseMMap == nil) ||
(opts.UseMMap != nil && !*opts.UseMMap) {
params = append(params, "--no-mmap")