mirrors/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-05-11 10:26:53 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

some gocritic

Browse source
This commit is contained in:
Michael Yang 2024-05-21 22:07:57 -07:00
parent dad7a987ae
commit c895a7d13f
10 changed files with 21 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

13
llm/server.go
View file

@ -104,21 +104,22 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
var layers int
layers, estimatedVRAM, estimatedTotal = EstimateGPULayers(gpus, ggml, projectors, opts)
if gpus[0].Library == "metal" && estimatedVRAM > systemMemory {
switch {
case gpus[0].Library == "metal" && estimatedVRAM > systemMemory:
// disable partial offloading when model is greater than total system memory as this
// can lead to locking up the system
opts.NumGPU = 0
} else if gpus[0].Library != "metal" && layers == 0 {
case gpus[0].Library != "metal" && layers == 0:
// Don't bother loading into the GPU if no layers can fit
cpuRunner = serverForCpu()
gpuCount = 0
} else if opts.NumGPU < 0 && layers > 0 && gpus[0].Library != "cpu" {
case opts.NumGPU < 0 && layers > 0 && gpus[0].Library != "cpu":
opts.NumGPU = layers
}
}
// Loop through potential servers
finalErr := fmt.Errorf("no suitable llama servers found")
finalErr := errors.New("no suitable llama servers found")
if len(adapters) > 1 {
return nil, errors.New("ollama supports only one lora adapter, but multiple were provided")
@ -284,7 +285,7 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
server := filepath.Join(dir, "ollama_llama_server")
if runtime.GOOS == "windows" {
server = server + ".exe"
server += ".exe"
}
// Detect tmp cleaners wiping out the file
@ -459,7 +460,7 @@ func (s *llmServer) getServerStatus(ctx context.Context) (ServerStatus, error) {
resp, err := http.DefaultClient.Do(req)
if err != nil {
if errors.Is(err, context.DeadlineExceeded) {
return ServerStatusNotResponding, fmt.Errorf("server not responding")
return ServerStatusNotResponding, errors.New("server not responding")
}
return ServerStatusError, fmt.Errorf("health resp: %w", err)
}