[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Author: pre-commit-ci[bot]

tests/model_serving/model_server/llmd/conftest.py

@@ -375,10 +375,10 @@ def singlenode_precise_prefix_cache(
                 "name": "VLLM_ADDITIONAL_ARGS",
                 "value": (
                     f"--prefix-caching-hash-algo {PREFIX_CACHE_HASH_ALGO} --block-size {PREFIX_CACHE_BLOCK_SIZE} "
-                    "--kv_transfer_config '{\"kv_connector\":\"NixlConnector\",\"kv_role\":\"kv_both\"}' "
-                    "--kv-events-config '{\"enable_kv_cache_events\":true,\"publisher\":\"zmq\","
-                    "\"endpoint\":\"tcp://{{ ChildName .ObjectMeta.Name `-epp-service` }}:5557\","
-                    "\"topic\":\"kv@${POD_IP}@${MODEL_NAME}\"}'"
+                    '--kv_transfer_config \'{"kv_connector":"NixlConnector","kv_role":"kv_both"}\' '
+                    '--kv-events-config \'{"enable_kv_cache_events":true,"publisher":"zmq",'
+                    '"endpoint":"tcp://{{ ChildName .ObjectMeta.Name `-epp-service` }}:5557",'
+                    '"topic":"kv@${POD_IP}@${MODEL_NAME}"}\''
                 ),
             },
             {

tests/model_serving/model_server/llmd/constants.py

@@ -41,4 +41,4 @@
             ],
         }
     ],
-}
+}

tests/model_serving/model_server/llmd/test_singlenode_precise_prefix_cache.py

@@ -28,6 +28,7 @@
 
 pytestmark = [pytest.mark.llmd_gpu]
 
+
 @pytest.mark.parametrize(
     "unprivileged_model_namespace",
     [pytest.param({"name": "singlenode-prefix-cache-test"})],

tests/model_serving/model_server/llmd/utils.py

@@ -265,17 +265,17 @@ def count_chat_completions_requests_in_pod(pod: Pod) -> int:
         logs = pod.log(container="main", since_seconds=120)
 
         # Match: "POST /v1/chat/completions HTTP/1.1" 200
-        pattern = r'POST /v1/chat/completions HTTP/1.1.*200'
+        pattern = r"POST /v1/chat/completions HTTP/1.1.*200"
         matches = re.findall(pattern, logs)
 
         LOGGER.info(f"Pod {pod.name}: Found {len(matches)} requests matching pattern")
 
         # Debug: Show sample log lines if no matches found
         if len(matches) == 0:
-            log_lines = logs.split('\n')
+            log_lines = logs.split("\n")
             LOGGER.info(f"Pod {pod.name}: Total log lines: {len(log_lines)}")
             # Show lines containing "POST" or "completions"
-            relevant_lines = [line for line in log_lines if 'POST' in line or 'completion' in line.lower()]
+            relevant_lines = [line for line in log_lines if "POST" in line or "completion" in line.lower()]
             if relevant_lines:
                 LOGGER.info(f"Pod {pod.name}: Sample relevant lines (first 5):")
                 for line in relevant_lines[:5]:
@@ -363,7 +363,7 @@ def verify_singlenode_prefix_cache_routing(
         inference_config = {
             "default_query_model": {
                 "query_input": repeated_prompt,
-                "query_output": r'.*',
+                "query_output": r".*",
                 "use_regex": True,
             },
             "chat_completions": TINYLLAMA_INFERENCE_CONFIG["chat_completions"],
@@ -411,7 +411,7 @@ def verify_singlenode_prefix_cache_routing(
         inference_config = {
             "default_query_model": {
                 "query_input": prompt,
-                "query_output": r'.*',
+                "query_output": r".*",
                 "use_regex": True,
             },
             "chat_completions": TINYLLAMA_INFERENCE_CONFIG["chat_completions"],