Search results

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

Status: Open.

#8877 In triton-inference-server/server;

· necropower opened on Jul 9, 2026

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

Status: Open.

#8874 In triton-inference-server/server;

· yiran-zhao opened on Jul 8, 2026

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

Status: Open.

#8870 In triton-inference-server/server;

· jimmystique opened on Jul 6, 2026

curl http://127.0.0.1:8000

Status: Open.

#8865 In triton-inference-server/server;

· azureai opened on Jun 30, 2026

Feature Request: OpenAI-Compatible Frontend for Python backend

Status: Open.

#8862 In triton-inference-server/server;

· oOTWK opened on Jun 29, 2026

Inaccuracies in PyTorch backend documentation

Documentation

documentation issueDocumentation isn't correct or could be improvedDocumentation isn't correct or could be improved

Status: Open.

#8853 In triton-inference-server/server;

· kpedro88 opened on Jun 24, 2026

json_schema support for OpenAI Frontend for Structured Outputs

Status: Open.

#8852 In triton-inference-server/server;

· jkim- opened on Jun 24, 2026

Timeline for ONNX Runtime 1.26.0 support in Triton releases?

Status: Open.

#8848 In triton-inference-server/server;

· jviehhauser opened on Jun 18, 2026

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

Status: Open.

#8843 In triton-inference-server/server;

· woxane opened on Jun 16, 2026

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

Status: Open.

#8841 In triton-inference-server/server;

· arpitagarwal-meesho opened on Jun 16, 2026

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

Status: Open.

#8840 In triton-inference-server/server;

· aleksn7 opened on Jun 15, 2026

Gradual queue-latency regime on TensorRT models with flat RSS and no GPU/host correlation — suspected scheduler-path lock contention

Status: Open.

#8839 In triton-inference-server/server;

· arpitagarwal-meesho opened on Jun 15, 2026