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.
1 parent 41802c5 commit 0781920Copy full SHA for 0781920
tools/server/tests/unit/test_chat_completion.py
@@ -271,8 +271,10 @@ def test_chat_completion_with_timings_per_token():
271
"max_tokens": 10,
272
"messages": [{"role": "user", "content": "test"}],
273
"stream": True,
274
+ "stream_options": {"include_usage": True},
275
"timings_per_token": True,
276
})
277
+ stats_received = False
278
for i, data in enumerate(res):
279
if i == 0:
280
# Check first role message for stream=True
@@ -288,6 +290,8 @@ def test_chat_completion_with_timings_per_token():
288
290
assert "predicted_per_second" in data["timings"]
289
291
assert "predicted_n" in data["timings"]
292
assert data["timings"]["predicted_n"] <= 10
293
+ stats_received = True
294
+ assert stats_received
295
296
297
def test_logprobs():
0 commit comments