Anthony Guselnikov
04/07/2025, 7:17 PMJian Shen Yap
04/07/2025, 7:25 PMAnthony Guselnikov
04/07/2025, 7:28 PMAnthony Guselnikov
04/07/2025, 7:28 PMFrost Ming
04/07/2025, 11:51 PMmax_latency_ms for batchable endpoints, not the timeout limit, the latter only returns a 504 errorFrost Ming
04/07/2025, 11:51 PM@bentoml.api(max_latency_ms=...)Anthony Guselnikov
04/08/2025, 12:43 PM@bentoml.service(
timeout=300,
traffic={"timeout": 300},
max_latency_ms=300_000
)
class SentenceTransformers:Anthony Guselnikov
04/08/2025, 12:43 PMAnthony Guselnikov
04/08/2025, 12:43 PM2025-04-08T08:40:24-0400 [INFO] [entry_service:SentenceTransformers:1] 127.0.0.1:64446 (scheme=http,method=POST,path=/encode,type=application/json,length=201092) (status=200,type=application/json,length=3425048) 151789.005ms (trace=5491b6186c17e30718f05b13090ed97c,span=18943e3dc8b2c9f2,sampled=0,service.name=SentenceTransformers)
2025-04-08T08:41:36-0400 [ERROR] [entry_service:SentenceTransformers:1] Exception on /encode [POST] (trace=312639eb08d8617a4ddb3e6b132f99ff,span=63493c48e2a8312c,sampled=0,service.name=SentenceTransformers)
Traceback (most recent call last):
File "/Users/guseant/.pyenv/versions/3.12.6/lib/python3.12/site-packages/bentoml/_internal/marshal/dispatcher.py", line 189, in _func
r = await self.inbound_call(data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/guseant/.pyenv/versions/3.12.6/lib/python3.12/site-packages/bentoml/_internal/marshal/dispatcher.py", line 334, in inbound_call
return await future
^^^^^^^^^^^^
asyncio.exceptions.CancelledError
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/Users/guseant/.pyenv/versions/3.12.6/lib/python3.12/site-packages/_bentoml_impl/server/app.py", line 604, in api_endpoint_wrapper
resp = await self.api_endpoint(name, request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/guseant/.pyenv/versions/3.12.6/lib/python3.12/site-packages/_bentoml_impl/server/app.py", line 688, in api_endpoint
output = await self.batch_infer(name, call_args, call_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/guseant/.pyenv/versions/3.12.6/lib/python3.12/site-packages/_bentoml_impl/server/app.py", line 596, in batch_infer
return await self.dispatchers[name](
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/guseant/.pyenv/versions/3.12.6/lib/python3.12/site-packages/bentoml/_internal/marshal/dispatcher.py", line 191, in _func
return self.fallback()
^^^^^^^^^^^^^^^
File "/Users/guseant/.pyenv/versions/3.12.6/lib/python3.12/site-packages/_bentoml_impl/server/app.py", line 118, in fallback
raise ServiceUnavailable("process is overloaded")
bentoml.exceptions.ServiceUnavailable: process is overloaded
2025-04-08T08:41:36-0400 [INFO] [entry_service:SentenceTransformers:1] 127.0.0.1:64590 (scheme=http,method=POST,path=/encode,type=application/json,length=201092) (status=503,type=application/json,length=74) 60015.561ms (trace=312639eb08d8617a4ddb3e6b132f99ff,span=63493c48e2a8312c,sampled=0,service.name=SentenceTransformers)Anthony Guselnikov
04/08/2025, 12:47 PMAnthony Guselnikov
04/08/2025, 12:56 PMAnthony Guselnikov
04/08/2025, 12:56 PM