search

triton-inference-server / fastertransformer_backend

BSD 3-Clause "New" or "Revised" License
411 stars 133 forks source link

Use the Triton client to call the interface asynchronously and call the interface concurrently, and the result is empty #92

Closed PAOPAO6 closed 1 year ago

PAOPAO6 commented 1 year ago

Description

model: mt5:
triton version: 22.10
gpu: T4

api:
client.async_infer

Reproduced Steps

Refer to the figure below for details
PAOPAO6 commented 1 year ago

14536_14

PAOPAO6 commented 1 year ago

result = async_request.get_result()
result is none