ELTC: An End-to-End Large Language Model-Based Tensor Compilation Optimization Framework
Abstract elided by the publisher.
Related papers
- Fast Autoscheduling for Sparse ML Frameworks CGO 2026
- FlashTensor: Optimizing Tensor Programs by Leveraging Fine-grained Tensor Property PPoPP 2025
- One-shot tuner for deep learning compilers CC 2022
- Tenspiler: A Verified-Lifting-Based Compiler for Tensor Operations ECOOP 2024
- Hexcute: A Compiler Framework for Automating Layout Synthesis in GPU Programs CGO 2026
- MetaKernel: Enabling Efficient Encrypted Neural Network Inference through Unified MVM and Convolution OOPSLA 2025
- oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation CGO 2024
- High-Throughput Non-uniformly Quantized 3-bit LLM Inference PPoPP 2026