A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 11:00 UTC
[Bugfix] Fix entrypoints audio test failure (#18111)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
May 14, 2025 at 17:08 UTC
8f5dc41481b7621f89ea203a40fdfbacfee3a44a
1 file changed
+4
-4
tests/entrypoints/openai/test_audio.py
+4
-4
@@ -272,7 +272,7 @@ async def test_chat_streaming_audio(client: openai.AsyncOpenAI,
272
chat_completion = await client.chat.completions.create(
273
model=model_name,
274
messages=messages,
275
- max_completion_tokens=10,
275
+ max_completion_tokens=8,
276
temperature=0.0,
277
)
278
output = chat_completion.choices[0].message.content
@@ -282,7 +282,7 @@ async def test_chat_streaming_audio(client: openai.AsyncOpenAI,
282
stream = await client.chat.completions.create(
283
model=model_name,
284
messages=messages,
285
- max_completion_tokens=10,
285
+ max_completion_tokens=8,
286
temperature=0.0,
287
stream=True,
288
)
@@ -332,7 +332,7 @@ async def test_chat_streaming_input_audio(client: openai.AsyncOpenAI,
332
chat_completion = await client.chat.completions.create(
333
model=model_name,
334
messages=messages,
335
- max_completion_tokens=10,
335
+ max_completion_tokens=8,
336
temperature=0.0,
337
)
338
output = chat_completion.choices[0].message.content
@@ -342,7 +342,7 @@ async def test_chat_streaming_input_audio(client: openai.AsyncOpenAI,
342
stream = await client.chat.completions.create(
343
model=model_name,
344
messages=messages,
345
- max_completion_tokens=10,
345
+ max_completion_tokens=8,
346
temperature=0.0,
347
stream=True,
348
)