fix server embedding test

examples/server/tests/features/embeddings.feature

@@ -9,6 +9,7 @@ Feature: llama.cpp server
     And   42 as server seed
     And   2 slots
     And   1024 as batch size
+    And   1024 as ubatch size
     And   2048 KV cache size
     And   embeddings extraction
     Then  the server is starting

examples/server/tests/features/steps/steps.py

@@ -33,6 +33,7 @@ def step_server_config(context, server_fqdn, server_port):
 
     context.model_alias = None
     context.n_batch = None
+    context.n_ubatch = None
     context.n_ctx = None
     context.n_ga = None
     context.n_ga_w = None
@@ -278,6 +279,11 @@ def step_n_batch(context, n_batch):
     context.n_batch = n_batch
 
 
+@step('{n_ubatch:d} as ubatch size')
+def step_n_ubatch(context, n_ubatch):
+    context.n_ubatch = n_ubatch
+
+
 @step('{seed:d} as seed')
 def step_seed(context, seed):
     context.seed = seed
@@ -1029,6 +1035,8 @@ def start_server_background(context):
     ]
     if context.n_batch:
         server_args.extend(['--batch-size', context.n_batch])
+    if context.n_ubatch:
+        server_args.extend(['--ubatch-size', context.n_ubatch])
     if context.n_gpu_layer:
         server_args.extend(['--n-gpu-layers', context.n_gpu_layer])
     if context.server_continuous_batching: