From cef3cf353ac964a818a9e8a1cecb7a3cfd6a617a Mon Sep 17 00:00:00 2001
From: Michael Yang <mxyng@pm.me>
Date: Fri, 20 Dec 2024 13:39:51 -0800
Subject: [PATCH] estimate log value

---
 llm/memory.go | 6 +++---
 llm/server.go | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/llm/memory.go b/llm/memory.go
index fdfe798f9..2f930d75f 100644
--- a/llm/memory.go
+++ b/llm/memory.go
@@ -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
diff --git a/llm/server.go b/llm/server.go
index 134f5d8a3..dc38979ca 100644
--- a/llm/server.go
+++ b/llm/server.go
@@ -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")