highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-04-11 21:29:32 +02:00
Code Issues Packages Projects Releases Wiki Activity

estimate log value

Browse Source
This commit is contained in:
Michael Yang 2024-12-20 13:39:51 -08:00
parent 512bbb8044
commit cef3cf353a
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
llm/memory.go
View File

@ -338,7 +338,7 @@ func EstimateGPULayers(gpus []discover.GpuInfo, f *ggml.GGML, projectors []strin
return estimate
}
func (m MemoryEstimate) log() {
func (m MemoryEstimate) LogValue() slog.Value {
overhead := envconfig.GpuOverhead()
log := slog.With()
@ -352,8 +352,8 @@ func (m MemoryEstimate) log() {
)
}
log.Info(
"offload to "+m.inferenceLibrary,
return slog.GroupValue(
slog.String("library", m.inferenceLibrary),
slog.Group(
"layers",
// requested number of layers to offload

2
llm/server.go
View File

@ -139,7 +139,7 @@ func NewLlamaServer(gpus discover.GpuInfoList, model string, f *ggml.GGML, adapt
}
}
estimate.log()
slog.Info("offload", "", estimate)
// Loop through potential servers
finalErr := errors.New("no suitable llama servers found")