A guidance language for controlling large language models.

Intel confidential computing - TDX

Efficient and general syntactical decoding for Large Language Models

Record and Replay Framework

derive builder implementation for rust structs

Google Research

Parsers for CUDA binary files

Distributed LLM inference for mobile, desktop and server.

Open Source Architecture Code Analyzer

CUDA on ??? GPUs

Rust library for build scripts to compile C/C++ code into a Rust library

Framework and Language for Neurosymbolic Programming. Join Our Discord: https://discord.gg/RavzdND229

my blog

A native gRPC client & server implementation with async/await support.

A retargetable MLIR-based machine learning compiler and runtime toolkit.

LLM inference in C/C++

GEF (GDB Enhanced Features) - a modern experience for GDB with advanced debugging capabilities for exploit devs & reverse engineers on Linux

Dynamic function call interposition / hooking (LD_PRELOAD) for Rust

Safe rust wrapper around CUDA toolkit

A cross-platform detour library written in Rust

A cross-platform detour library written in Rust

你知道我要说什么

Tensor library for machine learning

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

[Unmaintained, see README] An ecosystem of Rust libraries for working with large language models

Apple SEP reverse

Practical GPU Sharing Without Memory Size Constraints

cricket is a virtualization solution for GPUs

qCUDA: GPGPU Virtualization at a New API Remoting Method with Para-virtualization