PyTorch-Triton 3.7 Adds Runtime Extensions
PyTorch · x · 2026-07-16
PyTorch-Triton 3.7 has been released, introducing the Triton Plugin Extensions system.
This mechanism allows for the dynamic loading of custom compiler passes, dialect ops, and DSL extensions at runtime, extending upstream Triton directly without the need for forking or recompiling.
Official technical deep-dive articles and getting started guides are also provided. This update is highly useful for teams needing compiler or operator-level customization on Triton.
More from Infra
- llama.cpp lands Flash Attention tuning for RDNA4, big prefill gains on AMD — pmttyji · 2026-09-11
- Your p99 latency benchmark may be lying: a deep dive into coordinated omission — Franc0Fernand0 · 2026-09-11
- Running MiniMax H3 on 12GB VRAM: quantization, Turbo LoRAs and attention backends compared — Possible_Mood676 · 2026-09-11
- Spomin: live KV cache compaction squeezes 500k tokens of context into 180k resident — wgaca2 · 2026-09-11
- PiPNN nearest-neighbor search wins three awards, up to 78x faster index building — khademinori · 2026-09-11
- M.2-Oculink eGPU Link Silently Downgrades to PCIe Gen1 — Here's How to Check — El_90 · 2026-09-11