nncase: An End-to-End Compiler for Efficient LLM Deployment on Heterogeneous Storage Architectures

TL;DR

nncase is an open-source compiler framework that optimizes large language model deployment across diverse hardware architectures by unifying various optimization strategies and reducing adaptation complexity.

Contribution

It introduces an end-to-end compilation framework with an e-graph-based engine and automated modules for vectorization, distribution, and scheduling, improving deployment efficiency.

Findings

Outperforms mainstream frameworks on Qwen3 models

Achieves CPU performance comparable to hand-optimized code

Effectively unifies optimization across heterogeneous hardware

Abstract

The efficient deployment of large language models (LLMs) is hindered by memory architecture heterogeneity, where traditional compilers suffer from fragmented workflows and high adaptation costs. We present nncase, an open-source, end-to-end compilation framework designed to unify optimization across diverse targets. Central to nncase is an e-graph-based term rewriting engine that mitigates the phase ordering problem, enabling global exploration of computation and data movement strategies. The framework integrates three key modules: Auto Vectorize for adapting to heterogeneous computing units, Auto Distribution for searching parallel strategies with cost-aware communication optimization, and Auto Schedule for maximizing on-chip cache locality. Furthermore, a buffer-aware Codegen phase ensures efficient kernel instantiation. Evaluations show that nncase outperforms mainstream frameworks like MLC LLM and Intel IPEX on Qwen3 series models and achieves performance comparable to the hand-optimized llama.cpp on CPUs, demonstrating the viability of automated compilation for high-performance LLM deployment. The source code is available at https://github.com/kendryte/nncase.