From c4014e73a25488b3f1488b96e82b578d8261993f Mon Sep 17 00:00:00 2001
From: Daniel Hiltgen <daniel@ollama.com>
Date: Fri, 10 May 2024 15:09:48 -0700
Subject: [PATCH] Fall back to CPU runner with zero layers

---
 llm/server.go | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/llm/server.go b/llm/server.go
index 81a2dec4..33c56f1f 100644
--- a/llm/server.go
+++ b/llm/server.go
@@ -105,6 +105,10 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
 			// 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 {
+			// 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" {
 			opts.NumGPU = layers
 		}