👷 Build compute kernels

A high-throughput and memory-efficient inference and serving engine for LLMs

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…

Kernel sources for https://huggingface.co/kernels-community

Playgound for homelab-related NixOS experiments

Load compute kernels from the Hub

Navidrome's documentation website

OBSE64 template using CommonLibOB64

Rust client for the huggingface hub aiming for minimal subset of features over `huggingface-hub` python package

A Datacenter Scale Distributed Inference Serving Framework

NVIDIA Inference Xfer Library (NIXL)

Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)

Curated transformers

Unreal Engine 5.3.2 project for Oblivion

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Eole blows gently into your ear his nicest melodies.

Tool for making your CSV files ready to import into YNAB

Milk-V Duo official C/C++ examples

🔍 LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your d…

This is a collection of stuff that I wrote for Proxmox.

A collaborative reverse-engineered library for Starfield

Additional packages (components, document stores and the likes) to extend the capabilities of Haystack version 2.0 and onwards

Large Language Model Text Generation Inference

Manages address library and IDA names

Address libraries for games