8000
We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
2 parents 5da5773 + 3d5e5b1 commit cf8ae5aCopy full SHA for cf8ae5a
llama_cpp/server/app.py
@@ -1,5 +1,6 @@
1
import json
2
import multiprocessing
3
+import time
4
from re import compile, Match, Pattern
5
from threading import Lock
6
from functools import partial
@@ -271,7 +272,11 @@ def get_route_handler(
271
272
273
async def custom_route_handler(request: Request) -> Response:
274
try:
- return await original_route_handler(request)
275
+ start_sec = time.perf_counter()
276
+ response = await original_route_handler(request)
277
+ elapsed_time_ms = int((time.perf_counter() - start_sec) * 1000)
278
+ response.headers["openai-processing-ms"] = f"{elapsed_time_ms}"
279
+ return response
280
except Exception as exc:
281
json_body = await request.json()
282
0 commit comments