Repository Issue Activity (beta)

#8808 Bug: cudnn_conv_algo_search silently ignored when configured via CUDA gpu_execution_accelerator

#8813 Example: FunASR/SenseVoice speech recognition model on Triton

#8805 [Compatibility Request] Support TensorRT-LLM v1.3 in Triton Inference Server containers

#8767 Bug: tritonserver crashes with Exit Code 141 (SIGPIPE) when loading models from S3 due to idle connection timeout

#8300 Critical Risk: PyTorch Backend Relies on Unmaintained TorchScript

#8786 Status inquiry on submitted PSIRT vulnerability reports for Triton Inference Server

#8740 Ensemble Model only marginally faster than separate single-model calls -- is this expected?

#8790 [BUG] --http-header-forward-pattern has no effect on /generate endpoint (ensemble → Python backend)

#7484 module 'triton' has no attribute 'language'

#8781 Stuck in PENDING to EXECUTING state : full model

#8653 Is ragged_batching support in ensemble?

#8663 Segmentation fault on model reload when using Python backend metrics due to shared Metric object across processes

#8776 Preprocessing in ensemble 2x slower than preprocessing on client side

#8699 speculative config with vllm backend

#8462 GitHub::Issue - build error

#8762 SageMaker single-model endpoint returns 500 for empty-body POST to /invocations (should be 400)

#8537 Cannot remove future from background; KeyError: <Future at ... state=finished returned NoneType>

#8620 tensorrt and tensorrtllm in the same image

#8410 cmake build - windows 11 - This file was generated by a newer version of protoc

#8398 Configuration Options for OpenTelemetry Tracing for Fewer Spans

#8401 Add Support for Key-Based Batching

#8766 Python backend model missing model.py remains stuck in LOADING and cannot be unloaded

#8715 Why Does KIND_MODEL Validation Forbid `gpus` Field when Backend API Supports `device_id` for All Instance Kinds

#8301 [Server] Support for numpy2.x

#8540 Get stuck on the stage "Engine version 1.0.0 found in the config file, assuming engine(s) built by new builder API."