Triton Inference Server GitHub repository

Fields

id

sources/niche-triton-repo

URL

https://github.com/triton-inference-server/server

Publisher

NVIDIA

Kind

repo

Accessed

2026-10-03

notes

Triton server README (r26.09 line). Dynamic batching and sequence batching, model ensembles, a filesystem model repository, and a Python backend as the extension point. The 26.09 container release on NVIDIA GPU Cloud is called out explicitly. Vendor project, so the feature claims are NVIDIA's. API metadata 2026-10-03: created 2018-10-04, last push 2026-10-03, v2.73.0 (2026-09-30), BSD-3-Clause, 4163 open issues, 11042 stars.

Notes

Triton server README (r26.09 line). Dynamic batching and sequence batching, model ensembles, a filesystem model repository, and a Python backend as the extension point. The 26.09 container release on NVIDIA GPU Cloud is called out explicitly. Vendor project, so the feature claims are NVIDIA's. API metadata 2026-10-03: created 2018-10-04, last push 2026-10-03, v2.73.0 (2026-09-30), BSD-3-Clause, 4163 open issues, 11042 stars.

Cross-references

This record references no other records.