Triton 编译器发布: Triton 3.6.0 release

来源摘要

# Triton 3.6 Release Notes ## Table of Contents - [Dialect & Frontend](#dialect--frontend) - [Backend & Compiler](#backend--compiler) - [AMD/HIP Backend](#amdhip-backend) - [NVIDIA Backend](#nvidia-backend) - [Gluon & Layout Improvements](#gluon--layout-improvements) - [Kernels & Benchmarks](#kernels--benchmarks) - [Proton Profiling](#proton-profiling) - [Testing & CI](#testing--ci) - [Build & Infrastructure](#build--infrastructure) - [Documentation](#documentation) - [Breaking Changes](#breaking-changes) --- ## Dialect & Frontend ### New Features - **Multidimensional Batch Support** (#8542): Added support for multidimensional batches in `tl.trans` and `tl.dot` operations - **Ragged TMA Atomic Add** (#8238): Added atomic add support for ragged TMA operations - **Integer Range Utility** (#8753): Exposed an integer-range utility from AMD range analysis code for broader use - **Constexpr Through Min/Max** (#8733): Propagate constexpr through builtin min/max functions (BC-breaking) - **Scales Dimension Checks** (#8564): Added dimension checks for scales in `dot_scaled` operations - **Loop Bounds Verification** (#8243): Added verification that loop bounds are scalars ### Bug Fixes - **For Loop Induction Variable** (#8750): Fixed modification of for loop induction variable handling - **Store Broadcasting** (#8661): Fixed broadcasting issues in store operations - **Missing `dot_scaled` Handling** (#8658): Fixed missing handling for None acc in `dot_scaled` - **AugAssign Line Information** (#8703): Attached proper line number information to AugAssign nodes - **Starred Argument Handling** (#8686): Made starred argument handling more robust - **Saved Exception Cloning** (#8115): Fixed clone of saved exception before raising - **Tuple Mangling** (#8060): Fixed mangling for tuples