Comments (5)
Another interesting thing we just noticed is that, when our redis instance went down for a few minutes and when the pods lost connection to it, all of our triton servers had this same segmentation fault at the same time and all restarted. Not sure if that is this pattern is the same reason we are seeing those core dumps intermittently, but either way, those segmentation faults seem like unexpected behavior.
from server.
@rahchuenmonroe we would appreciate if you could experiment and give us more concrete steps to reproduce the issue.
from server.
[6861] created for tracking
from server.
Our prior version was 2.44.0 and we never saw this issue before. We also started using redis caching for ensembles in this version.
In addition to @statiraju comment about providing reproduction steps, it would be great if you could also try simplifying the set of things that changed to help isolate the issue. For example, two experiments:
- 24.04 vs 24.05 both with no redis caching, see if 24.05 introduces failure
- 24.05 no redis caching vs. 24.05 with redis caching, see if redis caching introduces failure
from server.
To clarify, we were using 24.03 prior and now are using 24.05 because of ensemble caching.
So far:
24.05, caching enabled: pods restart after core dumps.
24.05, caching disabled: no restarts.
24.03, caching disabled: no restarts.
Can't test for 24.03 with caching enabled since ensemble caching is only in latest version.
The only way I have been able to somewhat accidentally reproduce this was when the redis instance went down for a few minutes during an update and then all pods core dumped. I'm not sure if that's something you folks can somewhat reproduce? Although it's hard to say that is what is happening intermittently also, it does seem a bit suspicious. And from my understanding, if the redis caching request fails, the request should be processed normally instead, so losing connection to redis should not restart the server.
Let me know if I can provide any more information on this, thanks for looking into this!
from server.
Related Issues (20)
- could you give some examples about ragged input config for tensorrt backend HOT 5
- Large latency when use `tritonclient.http.aio.infer` HOT 3
- tritonserver log problem
- The trt llm container does not have the other backends HOT 7
- Regression from 23.07 to 24.05 on model count lifecycle/restarts HOT 4
- Triton/vllm_backend launches model on incorrect GPU
- Add torch.set_float32_matmul_precision settting in Libtorch backend
- Question about the `get_response()` function in the Python API's HTTP/REST Client
- Triton ensemble not working as expected to support reshape HOT 1
- nvcr.io: i/o timeout - error 401 HOT 1
- How to use pb_utils in python backend to receive data from cudashm?
- why is only 1st 'batch' inferred?
- How does the stateful model maintain state among multiple pods? HOT 3
- Minimal Custom Backend Example Not Working
- Model 'tensorrt_llm' loading failed with error: key 'use_context_fmha_for_generation' not found HOT 3
- Dynamic batching with OpenVINO backend
- In BLS mode, does the data go to the CPU HOT 2
- Handling Unsupported Input and Ensuring GPU Processing in Triton Inference Server HOT 1
- Using output of a model as input for multiple other models in ensemble give unclear error HOT 2
- my label_filename don't read I have class0 for label 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 server.