Skip to content

Issues: triton-inference-server/server

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

551 Open 3,191 Closed
551 Open 3,191 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Encountering stuck situations when using both Triton client and multiprocessing simultaneously
#7690 opened Oct 9, 2024 by Soul-Code
Segmentation fault
#7689 opened Oct 9, 2024 by lizhenneng
Possible bug in reference counting with shared memory regions investigating The developement team is investigating this issue
#7688 opened Oct 8, 2024 by hcho3
@pskiran1
The pth model to the triton pt model failed
#7685 opened Oct 8, 2024 by linsistqb
Ability to do casting between datatypes within backend
#7680 opened Oct 4, 2024 by kronoker
are FP8 models supported in Triton ?? question Further information is requested
#7678 opened Oct 4, 2024 by jayakommuru
7
Triton ONNX runtime backend slower than onnxruntime python client on CPU performance A possible performance tune-up
#7677 opened Oct 3, 2024 by Mitix-EPI
Histogram Metric for multi-instance tail latency aggregation
#7672 opened Oct 1, 2024 by AshwinAmbal
1
DCGM unable to start: DCGM initialization error，Error: Failed to initialize NVML verify to close Verifying if the issue can be closed
#7670 opened Sep 29, 2024 by coder-2014
1
Error: ensemble of tensorrt + python_be + tensorrt is supported on jetson?
#7667 opened Sep 27, 2024 by olivetom
8
When there are multiple GPU, only one GPU is used question Further information is requested verify to close Verifying if the issue can be closed
#7664 opened Sep 27, 2024 by gyr66
4
Direct Streaming of Model Weights from Cloud Storage to GPU Memory enhancement New feature or request
#7660 opened Sep 26, 2024 by azsh1725
4
wired inference time for tritonserver
#7655 opened Sep 25, 2024 by qiuzhewei
1
Deploy TTS model with Triton and onnx backend, failed:Protobuf parsing failed investigating The developement team is investigating this issue question Further information is requested
#7654 opened Sep 25, 2024 by AnasAlmana
5
Big performance drop when using ensemble model over separate calls investigating The developement team is investigating this issue
#7650 opened Sep 24, 2024 by jcuquemelle
2
[Critical] Triton stops processing requests and crashes bug Something isn't working
#7649 opened Sep 24, 2024 by appearancefnp
@pskiran1
5
python_backend pytorch example as_numpy() error investigating The developement team is investigating this issue
#7647 opened Sep 24, 2024 by flian2
5
Make State Tensor Stay in Device Memory question Further information is requested
#7643 opened Sep 24, 2024 by poor1017
1
How many instances can Triton support for parallel inference at most?
#7641 opened Sep 22, 2024 by wwdok
incompatible constructor arguments for c_python_backend_utils.InferenceRequest investigating The developement team is investigating this issue question Further information is requested
#7639 opened Sep 20, 2024 by adrtsang
2
triton gpu deploy suddenly become very slow from 0.03s to 12s, how to solve it ? question Further information is requested
#7638 opened Sep 20, 2024 by yiluzhuimeng
1
./fetch_models.sh - unable to resolve host address
#7630 opened Sep 19, 2024 by surprisedPikachu007
1
[feature request] ffmpeg backend for simplifying decoding of audio/video inputs investigating The developement team is investigating this issue
#7629 opened Sep 19, 2024 by vadimkantorov
1
Does triton inference server support customers custom feature but do not need to modify the origin code, like some plugin feature? question Further information is requested
#7627 opened Sep 19, 2024 by GGBond8488
2
First invocation of model - Dynamic batching doesn't work - Python Backend
#7623 opened Sep 18, 2024 by ChristosCh00
ProTip! Add no:assignee to see everything that’s not assigned.