Skip to main content
Ctrl+K
nvsubquadratic 0.1.0 - Home nvsubquadratic 0.1.0 - Home

nvsubquadratic 0.1.0

nvsubquadratic 0.1.0 - Home nvsubquadratic 0.1.0 - Home

nvsubquadratic 0.1.0

Table of Contents

  • Overview
  • Getting Started
  • Architecture
  • Repository Overview
  • Examples
  • Benchmarks
  • Reports
  • Ops Overview
    • Mixed Boundary-Condition FFT Convolution
  • API Reference
    • Ops
    • Modules
    • Networks
    • Parallel
    • Core
    • Experiments
  • API Reference

API Reference#

Organised bottom-up: low-level convolution primitives first, then the mixer modules that compose them, then full networks, then the parallel, core utility, and experiments layers.

See ops/README.md for the math motivation behind the FFT-based ops, and docs-tracker.md at the repo root for the documentation coverage plan.

  • Ops
    • FFT convolutions (reference fp32)
    • FFT convolutions (CUDA-accelerated)
    • Direct 1D causal convolutions (CUDA-accelerated)
    • Circular FFT convolutions
    • Chunking utilities
    • Mixed boundary-condition FFT convolutions
  • Modules
    • Mixers
    • Convolutions
    • Kernels & filters
    • Normalization
    • Position encoding & patching
    • Gating & conditioning
    • Residual blocks
    • Schedulers
  • Networks
    • Classification & general-purpose
    • Baselines
  • Parallel
    • init_parallel_state
    • zigzag_split_across_group_ranks
    • zigzag_gather_from_group_ranks
    • setup_rank0_logging
    • AllToAllSingleFunction
  • Core
    • Lazy configuration
    • Initialisation helpers
    • QK normalization & rotary position embeddings
    • QuACK capability probe
    • Testing helpers
  • Experiments
    • Entry points
    • Configuration dataclasses
    • Lightning wrappers
    • Callbacks
    • Data modules
    • Utilities

previous

Mixed Boundary-Condition FFT Convolution

next

Ops

NVIDIA NVIDIA

Copyright © 2025-2026 NVIDIA Corporation.