Use monotonic time where appropriate (#1249)

2023-10-02 19:22:05 -07:00
parent 66d18a7fb0
commit acbed3ef40
7 changed files with 18 additions and 17 deletions
--- a/vllm/entrypoints/openai/api_server.py
+++ b/vllm/entrypoints/openai/api_server.py
@@ -210,7 +210,7 @@ async def create_chat_completion(request: ChatCompletionRequest,

    model_name = request.model
    request_id = f"cmpl-{random_uuid()}"
-    created_time = int(time.time())
+    created_time = int(time.monotonic())
    try:
        sampling_params = SamplingParams(
            n=request.n,
@@ -411,7 +411,7 @@ async def create_completion(request: CompletionRequest, raw_request: Request):
    if error_check_ret is not None:
        return error_check_ret

-    created_time = int(time.time())
+    created_time = int(time.monotonic())
    try:
        sampling_params = SamplingParams(
            n=request.n,