perf: build graph for next batch async to keep GPU busy (#11863)

* perf: build graph for next batch in parallel to keep GPU busy

This refactors the main run loop of the ollama runner to perform the main GPU
intensive tasks (Compute+Floats) in a go routine so we can prepare the next
batch in parallel to reduce the amount of time the GPU stalls waiting for the
next batch of work.

* tests: tune integration tests for ollama engine

This tunes the integration tests to focus more on models supported
by the new engine.

integration/api_test.go

@@ -390,7 +390,7 @@ func TestAPIEmbeddings(t *testing.T) {
 	client, _, cleanup := InitServerConnection(ctx, t)
 	defer cleanup()
 	req := api.EmbeddingRequest{
-		Model:  "orca-mini",
+		Model:  libraryEmbedModels[0],
 		Prompt: "why is the sky blue?",
 		Options: map[string]interface{}{
 			"temperature": 0,