Stars
LiteRT is the new name for TensorFlow Lite (TFLite). While the name is new, it's still the same trusted, high-performance runtime for on-device AI, now with an expanded vision.
A rewrite of the old legacy software "depends.exe" in C# for Windows devs to troubleshoot dll load dependencies issues.
syzkaller is an unsupervised coverage-guided kernel fuzzer
Mac OS X cross toolchain for Linux, FreeBSD, OpenBSD and Android (Termux)
eBPF-based Security Observability and Runtime Enforcement
The official pytorch implemention of the Intespeech 2024 paper "Reshape Dimensions Network for Speaker Recognition"
Up to 200x Faster Dot Products & Similarity Metrics — for Python, Rust, C, JS, and Swift, supporting f64, f32, f16 real & complex, i8, and bit vectors using SIMD for both AVX2, AVX-512, NEON, SVE, …
how to optimize some algorithm in cuda.
A modern model graph visualizer and debugger
Real-time face swap for PC streaming or video calls
A cheatsheet of modern C++ language and library features.
Benchmarks for some modern (2023) high-performance floating-point GEMM implementations compared to Mojo language
Build AI Assistants with memory, knowledge and tools.
You like pytorch? You like micrograd? You love tinygrad! ❤️
Distribute and run LLMs with a single file.
Granite Code Models: A Family of Open Foundation Models for Code Intelligence
🏗 Build container images for your Java applications.
official repository of aiXcoder-7B Code Large Language Model
Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".
A polyhedral compiler for expressing fast and portable data parallel algorithms
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges.
Telegram app which automates manual scanning through tons of Telegram messages looking for valuable information