Repository Issue Activity (beta)

#8884 Cuda SHM Module Cuda driver entry point API mismatch

#8882 Intermittent server crash (`boost::interprocess::lock_exception` / `std::bad_alloc` / SIGSEGV) in Python backend under concurrent BLS load — 25.02 (2.55.0)

#8240 UnicodeDecodeError: 'utf-8' codec can't decode byte 0xc4 in position 40692

#7594 GPU memory is not released by Triton

#8877 Error verifying Inductor: torch._inductor.config.triton.autotune does not exist

#8414 Support Pytorch AOTInductor

#8874 PT2/AOTI PyTorch backend reports incorrect compute_infer latency due to swapped ReportStatistics arguments

#8870 Dynamic-batcher throughput progressively degrades over time when `default_queue_policy.default_timeout_microseconds > 0` (waiting_consumer_count_ drift on payload merges)

#8869 Eval dataset for inference benchmarking docs

#8853 Inaccuracies in PyTorch backend documentation

#8865 curl http://127.0.0.1:8000

#8862 Feature Request: OpenAI-Compatible Frontend for Python backend

#8840 Python backend leaks disk: unpacked execution environments are never removed on model unload/reload

#7713 nv_inference_request_failure metric does not increase

#8393 length of requests in async function execute could be bigger than 1 when client sends input images with different shapes

#8655 triton+vllm serve embeddings but not support list[str]

#8474 Honor the sampling flag in traceparent header for OpenTelemetry tracing

#8444 openai-compatible frontend does not allow additional attributes at the request bodies, this would hinder adoption.

#8852 `json_schema` support for OpenAI Frontend for Structured Outputs

#8375 [Question] Different performance of vLLM server and Triton Inference Server

#8476 Build Docker image without TensorRT runtime

#8558 triton not suitable for live inference

#8848 Timeline for ONNX Runtime 1.26.0 support in Triton releases?

#8843 Iterative Sequences `force-end` at first state when use async execute

#8841 Python stub aborted with glibc heap corruption, leading to 0 RPS on gRPC serving thread