Merge pull request #30996 from vespa-engine/revert-30989-lesters/set-llama-threads-in-unit-testv8.334.22

Revert "Specifically set number of threads to use in llama unit test"

1 files changed, 5 insertions, 4 deletions

diff --git a/model-integration/src/test/java/ai/vespa/llm/clients/LocalLLMTest.java b/model-integration/src/test/java/ai/vespa/llm/clients/LocalLLMTest.java
index 95bcfb985bd..a3b260f3fb5 100644
--- a/model-integration/src/test/java/ai/vespa/llm/clients/LocalLLMTest.java
+++ b/model-integration/src/test/java/ai/vespa/llm/clients/LocalLLMTest.java
@@ -6,6 +6,7 @@ import ai.vespa.llm.completion.Completion;
 import ai.vespa.llm.completion.Prompt;
 import ai.vespa.llm.completion.StringPrompt;
 import com.yahoo.config.ModelReference;
+import org.junit.jupiter.api.Disabled;
 import org.junit.jupiter.api.Test;
 
 import java.util.ArrayList;
@@ -32,10 +33,10 @@ public class LocalLLMTest {
     private static Prompt prompt = StringPrompt.from("A random prompt");
 
     @Test
+    @Disabled
     public void testGeneration() {
         var config = new LlmLocalClientConfig.Builder()
                 .parallelRequests(1)
-                .threads(1)
                 .model(ModelReference.valueOf(model));
         var llm = new LocalLLM(config.build());
 
@@ -49,12 +50,12 @@ public class LocalLLMTest {
     }
 
     @Test
+    @Disabled
     public void testAsyncGeneration() {
         var sb = new StringBuilder();
         var tokenCount = new AtomicInteger(0);
         var config = new LlmLocalClientConfig.Builder()
                 .parallelRequests(1)
-                .threads(1)
                 .model(ModelReference.valueOf(model));
         var llm = new LocalLLM(config.build());
 
@@ -77,6 +78,7 @@ public class LocalLLMTest {
     }
 
     @Test
+    @Disabled
     public void testParallelGeneration() {
         var prompts = testPrompts();
         var promptsToUse = prompts.size();
@@ -88,7 +90,6 @@ public class LocalLLMTest {
 
         var config = new LlmLocalClientConfig.Builder()
                 .parallelRequests(parallelRequests)
-                .threads(1)
                 .model(ModelReference.valueOf(model));
         var llm = new LocalLLM(config.build());
 
@@ -116,6 +117,7 @@ public class LocalLLMTest {
     }
 
     @Test
+    @Disabled
     public void testRejection() {
         var prompts = testPrompts();
         var promptsToUse = prompts.size();
@@ -128,7 +130,6 @@ public class LocalLLMTest {
 
         var config = new LlmLocalClientConfig.Builder()
                 .parallelRequests(parallelRequests)
-                .threads(1)
                 .maxQueueSize(additionalQueue)
                 .model(ModelReference.valueOf(model));
         var llm = new LocalLLM(config.build());