added n_predict tests

Author: VJHack

examples/server/tests/features/n_predict.feature

@@ -0,0 +1,32 @@
+@llama.cpp
+@n_predict
+Feature: llama.cpp server
+
+  Background: Server startup
+    Given a server listening on localhost:8080
+    And   a model file test-model.gguf
+    And   a model alias tinyllama-2
+    And   42 as server seed
+    And   64 KV cache size
+    
+  Scenario: Generate N tokens
+    And   12 max tokens to predict
+    Then  the server is starting
+    Then  the server is healthy
+    Given a prompt:
+    """
+    Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
+    """
+    And   a completion request with no api error
+    Then  12 tokens are predicted 
+
+  Scenario: Generate tokens until context is full
+    And   -2 server max tokens to predict
+    Then  the server is starting
+    Then  the server is healthy
+    Given a prompt:
+    """
+    Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
+    """
+    And   a completion request with no api error
+    Then  11 tokens are predicted 

examples/server/tests/features/num_tokens.feature

@@ -159,7 +159,7 @@ def step_n_slots(context, n_slots: int):
 
 @step('{n_predict:d} server max tokens to predict')
 def step_server_n_predict(context, n_predict: int):
-    context.n_server_predict = n_predict if n_predict > 0 else None
+    context.n_server_predict = n_predict if n_predict > 0 or n_predict in (-1, -2) else None
 
 
 @step('{slot_save_path} as slot save path')