jeans/ollama
1
0
Fork 0
Code Issues Pull Requests Actions 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 return estimate
} }
func (m MemoryEstimate) log() { func (m MemoryEstimate) LogValue() slog.Value {
overhead := envconfig.GpuOverhead() overhead := envconfig.GpuOverhead()
log := slog.With() log := slog.With()
@ -352,8 +352,8 @@ func (m MemoryEstimate) log() {
) )
} }
log.Info( return slog.GroupValue(
"offload to "+m.inferenceLibrary, slog.String("library", m.inferenceLibrary),
slog.Group( slog.Group(
"layers", "layers",
// requested number of layers to offload // 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 // Loop through potential servers
finalErr := errors.New("no suitable llama servers found") finalErr := errors.New("no suitable llama servers found")