Sign in

Repository Index

96,838 visible repositories in the index

Tags: All Tags
Tags

A repository shows when it has any selected Tag.

Filters

Filters

Clear all filters

625–648 of 908 · Most stars

SquirrelJME is a Java ME 8 Virtual Machine for embedded and Internet of Things devices. It has the ultimate goal of being 99.9% compatible with the Java ME standard.

  • squirreljme
  • java
  • java-me
  • iot

A reasonably fast, easy to use and 100% conformant Elixir library for Google Protocol Buffers (aka protobuf)

  • protobuf
  • elixir
  • protocol-buffers
  • protobuf-message

Header-only, lightweight C++ library for binary streaming & serialization. Network data handling made easy peasy!

  • binary-stream
  • header-only
  • serialisation
  • serialization

TranslatedLiu Chunlin (刘春霖) AI Small Regular Script Studio · Online poetry calligraphy generation system (Copyright terms: free for personal use, paid for commercial use | Contact email for cooperation: [email protected])

An open source, reverse engineered and improved SteamVR lighthouse driver with support for both 1.0 and 2.0 lighthouses, with a custom firmware for 1.0 lighthouses to support more than 2 basestations at the same time!

[Tech Report] Simplifying and Improving On-Policy Distillation for Few-step Diffusion

  • diffusion
  • distillation
  • few-step-generation

Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.

Pure-Rust inference engine for Qwen GGUF models (Qwen3 to Qwen3.8, dense and MoE up to 770B+). CUDA and Vulkan (NVIDIA, AMD), hybrid CPU+GPU experts, MTP speculative decoding, OpenAI and Anthropic compatible server. Up to ~1.7x llama.cpp decode on a 12 GB RTX 3060.