Meta LLM Compiler! Meta proudly introduces the Meta LLM Compiler, a groundbreaking family of models built on the foundation of Meta Code Llama. These models bring advanced code optimization and compiler capabilities to the forefront. 🔍 𝗞𝗲𝘆 𝗙𝗲𝗮𝘁𝘂𝗿𝗲𝘀: - Emulate the compiler to predict optimal passes for code size. - Disassemble and analyze code with precision. - Fine-tune for new optimizations and compiler tasks. 📚 𝗘𝘅𝗽𝗹𝗼𝗿𝗲 𝗠𝗼𝗿𝗲: 👨💻HuggingFace Repository: https://lnkd.in/gAEubQTT 📝 Research Paper: https://lnkd.in/gjA-wfpT ✦ The LLM Compiler models set a new standard in code size optimization and disassembly, showcasing the evolving role of AI in assisting compiler experts to identify and apply optimizations effectively. ✦ Meta is thrilled to announce the release of the LLM Compiler 7B & 13B models under a permissive license for both research and commercial use. This initiative aims to empower developers and researchers to leverage these tools in their work and drive forward new innovations in this field.
Sunder Ali Khowaja , Ph.D., Senior Member IEEE’s Post
More Relevant Posts
-
Now this is exciting news! It seems every day a new or improved LLM model is announced. Each one with slightly improved characteristics, but mostly, at least from my perspective, of scientific interest. This however opens up quite some new use cases.💪 Working on development tools in the past myself, I'm curious to see how this will be productized eventually. #GenAI #AI
Today we’re releasing Meta LLM Compiler, a family of models built on Meta Code Llama with additional code optimization and compiler capabilities. The models achieve state-of-the-art results on optimization of code size and disassembly tasks. Hugging Face repo ➡️ https://go.fb.me/tdd3dw Research paper ➡️ https://go.fb.me/hvfnam LLM Compiler can emulate the compiler, predict optimal passes for code size, and disassemble code. It can be fine-tuned for new optimizations and compiler tasks. This work shows that AI is learning to optimize code and can assist compiler experts in identifying opportunities to apply optimizations. We believe this work could have an impact ranging from use in optimization for individual developer environments to inclusion in a compiler such as LLVM. We’re releasing LLM Compiler 7B & 13B models under a permissive license for both research and commercial use in the hopes of making it easier for developers and researchers alike to leverage this in their work and carry forward new research in this highly impactful space.
To view or add a comment, sign in
-
-
Pretrained on over 500B tokens of LLVM-IR, x86_84, ARM, and CUDA assembly codes, this is a breakthrough in compiler design using LLMs! Can't wait to see its effect on Edge AI optimization for resource constrained devices!
Today we’re releasing Meta LLM Compiler, a family of models built on Meta Code Llama with additional code optimization and compiler capabilities. The models achieve state-of-the-art results on optimization of code size and disassembly tasks. Hugging Face repo ➡️ https://go.fb.me/tdd3dw Research paper ➡️ https://go.fb.me/hvfnam LLM Compiler can emulate the compiler, predict optimal passes for code size, and disassemble code. It can be fine-tuned for new optimizations and compiler tasks. This work shows that AI is learning to optimize code and can assist compiler experts in identifying opportunities to apply optimizations. We believe this work could have an impact ranging from use in optimization for individual developer environments to inclusion in a compiler such as LLVM. We’re releasing LLM Compiler 7B & 13B models under a permissive license for both research and commercial use in the hopes of making it easier for developers and researchers alike to leverage this in their work and carry forward new research in this highly impactful space.
To view or add a comment, sign in
-
-
Here's why Meta LLM Compiler achieves state-of-the-art results in optimizing code size and disassembly tasks: 1. **Building on Code Llama:** Meta LLM Compiler takes the foundation of Code Llama, a large language model (LLM) specifically trained for code understanding. This provides a strong base for comprehending code structure and functionality. 2. **Enhanced Code Optimization and Compiler Reasoning:** The compiler goes beyond Code Llama's capabilities by being fine-tuned for tasks related to code optimization and understanding compiler actions. This specialization allows it to reason about the impact of optimizations and make informed suggestions. 3. **Focus on Intermediate Representations (IRs) and Assembly:** The model is trained on compiler intermediate representations (IRs) and assembly language. IRs are a format that compilers use internally to represent code, and assembly is a low-level language directly understandable by processors. By being familiar with these representations, the compiler can analyze code structure more effectively and identify optimization opportunities. 4. **Openly Available Pre-trained Models:** Meta provides a suite of pre-trained LLM Compiler models. These models are ready to use, allowing developers to leverage their capabilities without the need for extensive training from scratch. This accessibility fosters further research and development in code optimization. In summary, Meta LLM Compiler combines the strengths of Code Llama with additional training focused on compiler tasks and code representations. This specialization allows it to outperform previous models in optimizing code size and performing disassembly tasks.
Today we’re releasing Meta LLM Compiler, a family of models built on Meta Code Llama with additional code optimization and compiler capabilities. The models achieve state-of-the-art results on optimization of code size and disassembly tasks. Hugging Face repo ➡️ https://go.fb.me/tdd3dw Research paper ➡️ https://go.fb.me/hvfnam LLM Compiler can emulate the compiler, predict optimal passes for code size, and disassemble code. It can be fine-tuned for new optimizations and compiler tasks. This work shows that AI is learning to optimize code and can assist compiler experts in identifying opportunities to apply optimizations. We believe this work could have an impact ranging from use in optimization for individual developer environments to inclusion in a compiler such as LLVM. We’re releasing LLM Compiler 7B & 13B models under a permissive license for both research and commercial use in the hopes of making it easier for developers and researchers alike to leverage this in their work and carry forward new research in this highly impactful space.
To view or add a comment, sign in
-
-
Need to review(llvm)
Today we’re releasing Meta LLM Compiler, a family of models built on Meta Code Llama with additional code optimization and compiler capabilities. The models achieve state-of-the-art results on optimization of code size and disassembly tasks. Hugging Face repo ➡️ https://go.fb.me/tdd3dw Research paper ➡️ https://go.fb.me/hvfnam LLM Compiler can emulate the compiler, predict optimal passes for code size, and disassemble code. It can be fine-tuned for new optimizations and compiler tasks. This work shows that AI is learning to optimize code and can assist compiler experts in identifying opportunities to apply optimizations. We believe this work could have an impact ranging from use in optimization for individual developer environments to inclusion in a compiler such as LLVM. We’re releasing LLM Compiler 7B & 13B models under a permissive license for both research and commercial use in the hopes of making it easier for developers and researchers alike to leverage this in their work and carry forward new research in this highly impactful space.
To view or add a comment, sign in
-
-
More and more interest around LLM trained around advanced coding funcionalities... Cit. "There is increasing interest in large language models (LLMs) for software engineering tasks including code generation, code translation, and code testing"
Today we’re releasing Meta LLM Compiler, a family of models built on Meta Code Llama with additional code optimization and compiler capabilities. The models achieve state-of-the-art results on optimization of code size and disassembly tasks. Hugging Face repo ➡️ https://go.fb.me/tdd3dw Research paper ➡️ https://go.fb.me/hvfnam LLM Compiler can emulate the compiler, predict optimal passes for code size, and disassemble code. It can be fine-tuned for new optimizations and compiler tasks. This work shows that AI is learning to optimize code and can assist compiler experts in identifying opportunities to apply optimizations. We believe this work could have an impact ranging from use in optimization for individual developer environments to inclusion in a compiler such as LLVM. We’re releasing LLM Compiler 7B & 13B models under a permissive license for both research and commercial use in the hopes of making it easier for developers and researchers alike to leverage this in their work and carry forward new research in this highly impactful space.
To view or add a comment, sign in
-
-
✨✨Meta AI has introduced the Meta Large Language Model Compiler (LLM Compiler), a suite of large language models designed for code optimization. These models, based on Code Llama, are trained on a substantial dataset of 546 billion tokens of LLVM-IR (an intermediate representation used in the LLVM compiler framework) and assembly code, available in 7 billion and 13 billion parameter sizes. ✨✨Key Features: 🤖 Training Data: 546 billion tokens of LLVM-IR and assembly code. 🤖 Fine-tuning Data: Additional 164 billion tokens for tasks like flag tuning and disassembly. 🤖 Context Size: Supports a 16k token context window. 🤖 Pretraining Focus: Specializes in LLVM-IR and assembly code. #AI #MachineLearning #CompilerOptimization #LLM #MetaAI #CodeOptimization
Today we’re releasing Meta LLM Compiler, a family of models built on Meta Code Llama with additional code optimization and compiler capabilities. The models achieve state-of-the-art results on optimization of code size and disassembly tasks. Hugging Face repo ➡️ https://go.fb.me/tdd3dw Research paper ➡️ https://go.fb.me/hvfnam LLM Compiler can emulate the compiler, predict optimal passes for code size, and disassemble code. It can be fine-tuned for new optimizations and compiler tasks. This work shows that AI is learning to optimize code and can assist compiler experts in identifying opportunities to apply optimizations. We believe this work could have an impact ranging from use in optimization for individual developer environments to inclusion in a compiler such as LLVM. We’re releasing LLM Compiler 7B & 13B models under a permissive license for both research and commercial use in the hopes of making it easier for developers and researchers alike to leverage this in their work and carry forward new research in this highly impactful space.
To view or add a comment, sign in
-
-
#genAI: new offers in the open-source arena ▪️Meta has released Meta LLM Compiler. #LLMs are already widely used in software engineering for tasks such as ▪️generating code and documentation, ▪️translating code between programming languages, ▪️supporting testing and writing unit tests, and ▪️detecting and fixing bugs. In March 2024, researchers from Meta AI and Rice University introduced ▪️compiler optimization powered by LLMs with compiler feedback to optimize the code size of LLVM assembly. 📁 Article „Compiler generated feedback for Large Language Models“ on arXiv: https://lnkd.in/dJ3vzaBQ These developments facilitate that large open-source code datasets and Github-enabled models such as CodeLlama, ChatGPT, and Codex can help to develop a deeper understanding of various programming languages.
Today we’re releasing Meta LLM Compiler, a family of models built on Meta Code Llama with additional code optimization and compiler capabilities. The models achieve state-of-the-art results on optimization of code size and disassembly tasks. Hugging Face repo ➡️ https://go.fb.me/tdd3dw Research paper ➡️ https://go.fb.me/hvfnam LLM Compiler can emulate the compiler, predict optimal passes for code size, and disassemble code. It can be fine-tuned for new optimizations and compiler tasks. This work shows that AI is learning to optimize code and can assist compiler experts in identifying opportunities to apply optimizations. We believe this work could have an impact ranging from use in optimization for individual developer environments to inclusion in a compiler such as LLVM. We’re releasing LLM Compiler 7B & 13B models under a permissive license for both research and commercial use in the hopes of making it easier for developers and researchers alike to leverage this in their work and carry forward new research in this highly impactful space.
To view or add a comment, sign in
-
-
Meta LLM Compiler: Foundation Models for Code Compiler Optimization
Today we’re releasing Meta LLM Compiler, a family of models built on Meta Code Llama with additional code optimization and compiler capabilities. The models achieve state-of-the-art results on optimization of code size and disassembly tasks. Hugging Face repo ➡️ https://go.fb.me/tdd3dw Research paper ➡️ https://go.fb.me/hvfnam LLM Compiler can emulate the compiler, predict optimal passes for code size, and disassemble code. It can be fine-tuned for new optimizations and compiler tasks. This work shows that AI is learning to optimize code and can assist compiler experts in identifying opportunities to apply optimizations. We believe this work could have an impact ranging from use in optimization for individual developer environments to inclusion in a compiler such as LLVM. We’re releasing LLM Compiler 7B & 13B models under a permissive license for both research and commercial use in the hopes of making it easier for developers and researchers alike to leverage this in their work and carry forward new research in this highly impactful space.
To view or add a comment, sign in
-
-
Today we’re releasing Meta LLM Compiler, a family of models built on Meta Code Llama with additional code optimization and compiler capabilities. The models achieve state-of-the-art results on optimization of code size and disassembly tasks. Hugging Face repo ➡️ https://go.fb.me/tdd3dw Research paper ➡️ https://go.fb.me/hvfnam LLM Compiler can emulate the compiler, predict optimal passes for code size, and disassemble code. It can be fine-tuned for new optimizations and compiler tasks. This work shows that AI is learning to optimize code and can assist compiler experts in identifying opportunities to apply optimizations. We believe this work could have an impact ranging from use in optimization for individual developer environments to inclusion in a compiler such as LLVM. We’re releasing LLM Compiler 7B & 13B models under a permissive license for both research and commercial use in the hopes of making it easier for developers and researchers alike to leverage this in their work and carry forward new research in this highly impactful space.
To view or add a comment, sign in
-
-
Introducing AI at Meta LLM Compiler: - Designed for code optimization tasks - Built on Code Llama - Trained on 546B tokens - Available in 7B and 13B parameters This open source LLM boosts understanding of compiler IRs, assembly language, and optimization techniques. Model: https://lnkd.in/gfWDQrnt Paper: https://lnkd.in/eUn-NXr8
LLM Compiler - a facebook Collection
huggingface.co
To view or add a comment, sign in