diff --git a/llm/server.go b/llm/server.go index 9347a458..4e5dac28 100644 --- a/llm/server.go +++ b/llm/server.go @@ -258,7 +258,7 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr params = append(params, "--mlock") } - if gpu.IsNUMA() { + if gpu.IsNUMA() && gpus[0].Library == "cpu" { numaMode := "distribute" if runtime.GOOS == "linux" { if _, err := exec.LookPath("numactl"); err == nil {