Comments (1)
Triton provides the metrics api to allow an application to pull data. From there it's up to the pulling application to process the metrics, say a UI application. Tritonserver itself doesn't provide any of this UI functionality and is left up to the user to provide the front end they would like. Also consider the tracing api to get the raw trace data from requests on the server. Again, tritonserver itself doesn't provide a UI for this data.
from server.
Related Issues (20)
- CUDA Graph not work HOT 4
- [RFE] HandleGenerate equivalent for sagemaker_server.cc HOT 2
- The time spent on the inference request process far exceeds the model inference time. How can I determine where this additional time is being consumed?
- Casting NumPy string array to np_utils.Tensor disproportionately increases latency HOT 5
- On server/deploy/oci -> running "helm install example ." to deploy the Inference Server and pod doesn't get to running due to Liveness probe failed & Readiness probe failed HOT 1
- trt_profile_max_shapes not supported for ONNX-TRT backend HOT 1
- Failed to initialize Python stub + ModuleNotFoundError: No module named 'nvtabular', 'merlin' HOT 2
- does triton support different model-repository assemble into a batch? HOT 1
- Question: Which backends automatically warm up models? HOT 1
- [Question] Is it possible to shutdown Triton if we detect certain cuda errors ? HOT 1
- Perf Analyzer Error: Cannot send stop request without specifying a request_id HOT 1
- Python Backend: one model instance over multiple GPUs HOT 2
- Logs not getting generated with GRPC HOT 1
- Input data/shape validation HOT 7
- Manually update model repository index HOT 7
- Triton server execution is aborted in mac m3 pro as soon as a client sends a new request!!! HOT 2
- Unable to use triton client with shared memory in C++ (Jetpack 6 device) HOT 4
- ORT-TRT backend uses too much CPU memory HOT 1
- [TensorRT-LLM][ERROR] Received stop request for requestId 7772708 but it's not active (might be completed already). HOT 1
- Is onnxruntime-genai supported? HOT 2
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.