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

Merge pull request #4323 from dhiltgen/sort_by_free

Browse source 
Always use the sorted list of GPUs
This commit is contained in:
Daniel Hiltgen 2024-05-10 14:12:15 -07:00 committed by GitHub
commit 86f9b582d5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
server/sched.go
View file

@ -567,9 +567,9 @@ func pickBestFitGPUs(req *LlmRequest, ggml *llm.GGML, gpus gpu.GpuInfoList) gpu.
// - try subsets of GPUs instead of just falling back to 1 or all in a family
// Now try all the GPUs
if ok, estimatedVRAM = llm.PredictServerFit(gl, ggml, req.model.AdapterPaths, req.model.ProjectorPaths, req.opts); ok {
slog.Debug("new model will fit in available VRAM, loading", "model", req.model.ModelPath, "library", gl[0].Library, "required", format.HumanBytes2(estimatedVRAM))
return gl
if ok, estimatedVRAM = llm.PredictServerFit(sgl, ggml, req.model.AdapterPaths, req.model.ProjectorPaths, req.opts); ok {
slog.Debug("new model will fit in available VRAM, loading", "model", req.model.ModelPath, "library", sgl[0].Library, "required", format.HumanBytes2(estimatedVRAM))
return sgl
}
}
return nil