Comments (2)
Hi @DaniilKurlovich,
Looks like you are missing something in your setup.
I just tried your exact steps to repro, was unable to repro. Your client seems to have some minor issues attached working client below
My logs
I0325 23:39:50.100145 1 model.py:11] Params: {"top_k":10}
I0325 23:39:50.154021 1 model.py:10] Params: {"top_k":5}
I0325 23:39:50.157574 1 model.py:11] Params: {"top_k":7}
I0325 23:39:50.158148 1 model.py:10] Params: {"top_k":7}
My suggestions:
- Use the latest triton server version 24.02
- Modify you client
Client Code:
import asyncio
import numpy as np
import tritonclient.http.aio as tritonclient
from tritonclient.utils import np_to_triton_dtype
async def main():
texts = ['Text1', 'Text2', 'Text3', 'Text4']
preprocessed_data = np.array([e.encode('utf-8') for e in texts], dtype=np.object_)
client = tritonclient.InferenceServerClient(url='localhost:8090')
try:
infer_input = tritonclient.InferInput('INPUT_NAMES',
preprocessed_data.shape,
np_to_triton_dtype(preprocessed_data.dtype))
infer_input.set_data_from_numpy(preprocessed_data)
resp = await client.infer('stomp_1', [infer_input], outputs=[tritonclient.InferRequestedOutput('EXIT')],
parameters={'top_k': 10})
print(resp.as_numpy('EXIT'))
rand_matrix = resp.as_numpy('EXIT')
infer_input_2 = tritonclient.InferInput('INPUT', rand_matrix.shape,
np_to_triton_dtype(rand_matrix.dtype))
infer_input_2.set_data_from_numpy(rand_matrix)
resp2 = await client.infer('stomp_2', [infer_input_2], outputs=[tritonclient.InferRequestedOutput('EXIT_')],
parameters={'top_k': 5})
print(resp2.as_numpy('EXIT_'))
resp = await client.infer('stomp_ensemble', [infer_input], outputs=[tritonclient.InferRequestedOutput('ANSWER')],
parameters={'top_k': 7})
print(resp.as_numpy('ANSWER'))
finally:
await client.close()
if __name__ == '__main__':
asyncio.run(main())
from server.
Closing due to lack of activity. Please re-open the issue if you would like to follow up with this issue.
from server.
Related Issues (20)
- TritonSever does not register vLLM metrics HOT 1
- Problem with accumulating gpu memory usage in tritonserver
- I can't use vllm model from s3 model repository
- /v2/health/ready endpoint does not work as expected
- Implementing early exit in ensemble models HOT 2
- 50k-60k infer/sec limitation
- Ensemble Scheduler: Internal response allocation is not allocating memory at all HOT 3
- GPU memory is not released by Triton HOT 1
- Running separate DCGM on Kubernetes cluster
- Windows docker failed to load tritonserver module
- Can you add a feature : NanoFlow backend
- High GPU memory when load model use transformers HOT 2
- Why there aren't generate and generate_stream api in http client?
- Is it possible to imlement ensemble with BLS HOT 7
- Ability to make preferred_batch_size mandatory
- When downloading, execute ./fetch_models.sh the report
- What is the latest triton server release version available for jetpack 4.6.4 HOT 3
- version inconsistency:Tensorrt and Triton images HOT 1
- triton server python backend how to support streaming transmission
- failed to load all models 22.02
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from server.