A continuously updated collection of CodeLLM papers

Automatic testing tools with a general test oracle for detecting crashes and logic bugs in database systems

Enumerative Testing and Bounded Validation of SMT Solvers

[WIP] A JIT Compiler Fuzzer for JavaScript Engines

[TMLR] A curated list of language modeling researches for code (and other software engineering activities), plus related datasets.

Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.

Composable building blocks to build Llama Apps

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

An interpreter for Rust's mid-level intermediate representation

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

Missed optimizations in C compilers

Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Kythe is a pluggable, (mostly) language-agnostic ecosystem for building tools that work with code.

C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)

Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.

nanoGPT style version of Llama 3.1

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Utilities intended for use with Llama models.

Agentic components of the Llama Stack APIs

DLRover: An Automatic Distributed Deep Learning System

SGLang is a fast serving framework for large language models and vision language models.

The Memory layer for your AI apps

Ported scrcpy for mobile platforms, to remotely control Android devices on your iPhone or Android phone.

LLM (Large Language Model) FineTuning

surgical precision JIT compilers

Static Python call graph generator

Depends is a fast, comprehensive code dependency analysis tool

MetaMut is a mutation operator generator to facilitate compiler fuzzing.

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs