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

Improve logging on GPU too small (#6666)

Browse source 
When we determine a GPU is too small for any layers, it's not always clear why.
This will help troubleshoot those scenarios.
This commit is contained in:
Daniel Hiltgen 2024-09-06 08:29:36 -07:00 committed by GitHub
parent fe91d7fff1
commit 56318fb365
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 15 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
llm/memory.go
View file

@ -167,7 +167,21 @@ func EstimateGPULayers(gpus []gpu.GpuInfo, ggml *GGML, projectors []string, opts
}
// Only include GPUs that can fit the graph, gpu minimum, the layer buffer and at least more layer
if (gpus[i].FreeMemory - overhead) < gzo+max(graphPartialOffload, graphFullOffload)+gpus[i].MinimumMemory+2*layerSize {
slog.Debug("gpu has too little memory to allocate any layers", "gpu", gpus[i])
slog.Debug("gpu has too little memory to allocate any layers",
"id", gpus[i].ID,
"library", gpus[i].Library,
"variant", gpus[i].Variant,
"compute", gpus[i].Compute,
"driver", fmt.Sprintf("%d.%d", gpus[i].DriverMajor, gpus[i].DriverMinor),
"name", gpus[i].Name,
"total", format.HumanBytes2(gpus[i].TotalMemory),
"available", format.HumanBytes2(gpus[i].FreeMemory),
"minimum_memory", gpus[i].MinimumMemory,
"layer_size", format.HumanBytes2(layerSize),
"gpu_zer_overhead", format.HumanBytes2(gzo),
"partial_offload", format.HumanBytes2(graphPartialOffload),
"full_offload", format.HumanBytes2(graphFullOffload),
)
continue
}
gpusWithSpace = append(gpusWithSpace, gs{i, &gpus[i]})