A minimal static web server written in COBOL

Similar to Steel String Singer S/N #002

Browser-based tonestack calculator

the LLM vulnerability scanner

A Datacenter Scale Distributed Inference Serving Framework

An extremely fast Python package and project manager, written in Rust.

PyTorch compiler that accelerates training and inference. Get built-in optimizations for performance, memory, parallelism, and easily write your own.

AICI: Prompts as (Wasm) Programs

The Adventures of OS

Generate Go client and server boilerplate from OpenAPI 3 specifications

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

🦜🔗 Build context-aware reasoning applications

Simple, safe way to store and distribute tensors

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

Starlark implementation of bazel rules for CUDA.

Converts lcov output to Cobertura-compatible XML for CI

Goal: Enable awesome tooling for Bazel users of the C language family.

Standalone implementation of the CUDA-accelerated WFST Decoder available in Riva

Checklist for Tesla Model Y

Protocol buffers and other common resources.

Sample C++ command-line Riva clients.

BS::thread_pool: a fast, lightweight, modern, and easy-to-use C++17 / C++20 / C++23 thread pool library

C++ Requests: Curl for People, a spiritual port of Python Requests.

An efficient C++17 GPU numerical computing library with Python-like syntax

Locally squash commits on a branch without resolving any conflicts (a'la squash and merge)

Lightweight C++ command line option parser

TinyXML2 is a simple, small, efficient, C++ XML parser that can be easily integrated into other programs.

Generating bash command from natural language https://arxiv.org/abs/1802.08979

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