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

649 Open 3,241 Closed
649 Open 3,241 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

Question about 22.09 bug Something isn't working
#5098 opened Nov 22, 2022 by AkSino
4
Thread control options in PyTorch backend enhancement New feature or request
#5067 opened Nov 10, 2022 by kpedro88
3
allow constant input tensors in (ensemble) models enhancement New feature or request
#5037 opened Nov 4, 2022 by charlesmelby
2
Socket Closed when running on K8S bug Something isn't working
#5023 opened Nov 1, 2022 by avickars
1
Add example model for FIL backend enhancement New feature or request
#4942 opened Oct 3, 2022 by wphicks
@wphicks
Add support to "parameters" in Python tritonclient package enhancement New feature or request
#4919 opened Sep 23, 2022 by RafalSkolasinski
3
Python backend cannot import Tensor enhancement New feature or request
#4870 opened Sep 12, 2022 by Phelan164
6
Core rebuild is extremely long enhancement New feature or request
#4819 opened Aug 29, 2022 by alxmamaev
5
Show ensemble stage where error happens enhancement New feature or request
#4786 opened Aug 18, 2022 by alxmamaev
1
Container images for Jetson devices enhancement New feature or request
#4781 opened Aug 17, 2022 by rgov
4
Tests for backend examples enhancement New feature or request
#4779 opened Aug 17, 2022 by alxmamaev
3
Python Backend to support GPU instance enhancement New feature or request
#4772 opened Aug 16, 2022 by MhdKAT
9
Python Backend complains "triton_python_backend_utils" has no attribute "InferenceRequest" bug Something isn't working
#4743 opened Aug 5, 2022 by Michael-Jing
13
Fail to fetch PR with --repo-tag bug Something isn't working
#4725 opened Aug 2, 2022 by fgervais
3
One click deployment to GKE no longer works as Istio deprecated enhancement New feature or request investigating The developement team is investigating this issue
#4668 opened Jul 19, 2022 by samsaam-thg
6
Add source distribution to Python client package enhancement New feature or request
#4661 opened Jul 18, 2022 by janjagusch
1
2
[python backend] Add class_count argument for inference requests with BLS scripting enhancement New feature or request
#4647 opened Jul 14, 2022 by Rusteam
3
Dynamically loaded models don't work with ensemble bug Something isn't working investigating The developement team is investigating this issue
#4630 opened Jul 12, 2022 by fran6co
8
ONNXRuntime TensorRT cache gets regenerated every time a model is uploaded even with correct settings investigating The developement team is investigating this issue
#4587 opened Jul 5, 2022 by fran6co
1
6
Splitting a batch to max_batch_size if the batch size is larger than max_batch_size enhancement New feature or request investigating The developement team is investigating this issue
#4547 opened Jun 24, 2022 by omidb
17
[Question] Customize HTTP response status code for malformed GPU card bug Something isn't working investigating The developement team is investigating this issue
#4540 opened Jun 22, 2022 by pragyaarora
6
Support for the new CUDA virtual memory management functions for shared memory. enhancement New feature or request
#4538 opened Jun 22, 2022 by Reznic
6
support decoupled mode in perf_analyzer enhancement New feature or request
#4530 opened Jun 20, 2022 by Jackiexiao
1
SHARK Backend integration enhancement New feature or request
#4485 opened Jun 7, 2022 by powderluv
1
Torchscript backend **MUCH** slower only with FP16 on 1650 investigating The developement team is investigating this issue
#4451 opened May 31, 2022 by dmenig
7
ProTip! What’s not been updated in a month: updated:<2025-02-06.