Comments (3)
It looks like your model doesn't have any output. Is it expected? I think this error comes from Tensorflow side. Can you generate a single request using Triton clients to make sure that it works properly?
from model_analyzer.
Thanks! I've added the outputs and it works now. How long is it supposed to take? It's been stuck for 15 minutes now.
We're using the --strict-model-config=false
option for tritonserver, that's why the outputs were not set at first, is there a similar option with model-analyser? The outputs aren't relevant for the analysis, right?
from model_analyzer.
It can take a while to complete depending on your model. The add_sub model takes around 45 minutes on a TITAN RTX GPU. You can pass triton-server-flags
in the Model Analyzer Config. You can read more about it below:
from model_analyzer.
Related Issues (20)
- use of time intervals in model analyzer HOT 2
- [Bug] failed to load 'maxvit_rmlp_base', failed to poll from model repository (model_output path is the same) HOT 4
- How can i use perf_analyzer with python backend ? HOT 3
- Ensemble Model search error when specify perf_analyzer_flags.input-data HOT 3
- Model Analyzer - NO Gpu Metrics collection HOT 2
- Model Analyzer - NO Gpu Metrics collection
- Sending multiple shapes binary input data HOT 5
- Understanding GPU utilization HOT 5
- --triton-launch-mode=remote HOT 4
- custom samples HOT 1
- model analyser stuck HOT 2
- detailed report not generating HOT 2
- Time intervals in model analyzer
- UnicodeDecodeError: 'utf-8' codec can't decode byte 0xf8 in position 0: invalid start byte HOT 5
- How to sweep GPUs using Model Analyzer HOT 1
- How to analyze large models like llama 3 70B that requires model parallelism? HOT 3
- wrong with --triton-launch-mode=remote HOT 1
- DCGM initialization error HOT 1
- Deleted
- model_analyzer.model_analyzer_exceptions.TritonModelAnalyzerException: The first 2 attempts to acquire measurements have failed. HOT 1
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 model_analyzer.