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

576 Open 3,208 Closed
576 Open 3,208 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

Error about driver version compatibility module: platforms Issues related to platforms, hardware, and support matrix question Further information is requested
#7798 opened Nov 15, 2024 by GLW1215
@rmccorm4
2
Problems with the response of the OpenAI-Compatible Frontend for Triton Inference Server module: frontends Issues related to the triton frontends
#7796 opened Nov 14, 2024 by DimadonDL
@rmccorm4
1
Triton server receives Signal (11) when tracing is enabled with no sampling (or a small sampling rate) crash Related to server crashes, segfaults, etc.
#7795 opened Nov 14, 2024 by nicomeg-pr
@rmccorm4
1
ensemble multi-GPU module: server Issues related to the server core question Further information is requested
#7794 opened Nov 14, 2024 by xiazi-yu
@rmccorm4
2
有人遇到过yolov8n.pt模型转torchscripts和onnx，在triton server或Deepytorch Inference上推理，精度下降的问题吗？
#7792 opened Nov 14, 2024 by JackonLiu
Triton x vLLM backend GPU selection issue module: backends Issues related to the backends
#7786 opened Nov 13, 2024 by Tedyang2003
@rmccorm4
2
Constrained Decoding with Python backend and BLS module: backends Issues related to the backends
#7778 opened Nov 8, 2024 by MatteoPagliani
@rmccorm4
3
Example of using Ragged Batching with FasterTransformer / TRT-LLM for zero-padding BERT inference ("continuous batching")
#7777 opened Nov 8, 2024 by vadimkantorov
Unpredictability in Sequence batching performance A possible performance tune-up
#7776 opened Nov 8, 2024 by arun-oai
PyTorch model with Dictionary[Key,Tensor] output
#7765 opened Nov 5, 2024 by cesumilo
Do I need to warm up the model again after reloading it? question Further information is requested
#7762 opened Nov 4, 2024 by soulseen
@rmccorm4
1
How to deploy ensemble models of different versions more elegantly?
#7761 opened Nov 4, 2024 by lzcchl
1
StatusCode.UNAVAILABLE] Received http2 header with status: 502
#7760 opened Nov 3, 2024 by furkanc
Unable to simultaneously load TensorRT model.plan on different GPUs in Triton Inference Server in the same instance
#7755 opened Oct 30, 2024 by AntnvSergey
Build AMD64 Triton from ARM64 machine generate ARM64 architecture executable file build Issues pertaining to builds module: platforms Issues related to platforms, hardware, and support matrix
#7745 opened Oct 26, 2024 by ti1uan
@mc-nv @nv-kmcgill53
2
Handle raw binary request in python
#7741 opened Oct 24, 2024 by remiruzn
SeamlessM4T on triton
#7740 opened Oct 24, 2024 by Interwebart
Expensive & Volatile Triton Server latency performance A possible performance tune-up
#7739 opened Oct 24, 2024 by jadhosn
1
Running multi-gpu and replicating models question Further information is requested
#7737 opened Oct 24, 2024 by JoJoLev
@rmccorm4
1
Custom Image build doesn't detect Debian system build Issues pertaining to builds module: platforms Issues related to platforms, hardware, and support matrix
#7733 opened Oct 23, 2024 by VishDev12
@rmccorm4
1
Error building Triton Docker image in CPU-Only mode with TensorFlow2 backend build Issues pertaining to builds
#7732 opened Oct 23, 2024 by PierreCarceller
1
Failing CPU Build build Issues pertaining to builds question Further information is requested
#7731 opened Oct 23, 2024 by coder-2014
@KrishnanPrash
1
Triton is stopping, unexpectedly and without logging, when using a large model, s3 and periodical checks to ready and live endpoints
#7728 opened Oct 22, 2024 by smcbn
Memory Leak in NVIDIA Triton Server (v24.09-py3) with model-control-mode=explicit memory Related to memory usage, memory growth, and memory leaks
#7727 opened Oct 22, 2024 by Mustafiz48
@rmccorm4
6
Caught signal 11 (Segmentation fault: address not mapped to object at address 0x1c0) crash Related to server crashes, segfaults, etc. module: backends Issues related to the backends
#7723 opened Oct 21, 2024 by wxk-cmd
1
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.