Get the latest tech news
Meta Large Language Model Compiler
Large Language Models (LLMs) have demonstrated remarkable capabilities across a variety of software engineering and coding tasks. However, their...
Large Language Models (LLMs) have demonstrated remarkable capabilities across a variety of software engineering and coding tasks. The model has been trained on a vast corpus of 546 billion tokens of LLVM-IR and assembly code and has undergone instruction fine-tuning to interpret compiler behavior. We also present fine-tuned versions of the model, demonstrating its enhanced capabilities in optimizing code size and disassembling from x86_64 and ARM assembly back into LLVM-IR.
Or read this on Hacker News