DeepGEMM

Google's developer API for building applications with Gemini large language models. It provides access to models like Gemini 2.0 Flash and 2.5 Pro, and also supports Gemma open models. Developers use it for tasks such as custom model testing, retrieval, memory, and tool-calling systems.

DwarfStar is a self-contained, model-specific native inference engine for running DeepSeek V4 Flash, GLM 5.2, and, on high-memory systems, DeepSeek V4 PRO locally. It combines model loading, prompt rendering, tool calls, persistent KV state, an HTTP server, and a coding agent rather than serving as a general GGUF runner. The engine supports Metal on Macs, CUDA including multi-GPU systems, and ROCm on Strix Halo hardware; it also provides SSD streaming for machines with insufficient RAM, distributed tensor and pipeline parallelism, and server-side micro-batching for multi-user inference. The repository includes tooling and data for GGUF, imatrix, quality, and speed testing, and acknowledges code and design contributions from llama.cpp and GGML.

MoonEP is an expert-parallelism communication library from Moonshot AI for mixture-of-experts training and inference. It plans a small number of dynamic redundant experts from the current router outputs, prefetches their weights before expert computation, and reduces the resulting gradients back to the experts' home ranks during the backward pass. Its near-optimal GPU planning kernel, fused permute/unpermute operations, and zero-copy dispatch send tokens directly to expert-grouped positions on remote ranks and return buffer views to computation. The library uses a fixed S × K token buffer per rank, where S is the input-token count and K is the routed top-k, keeping communication and computation shapes static across layers. The repository documents support for NVIDIA GPUs and lists Zhenwu PPU support as under review.

Google DeepMind is an artificial-intelligence research and development organization that builds AI models and systems for general use, science, robotics, speech, image and video generation, music, and coding. Its featured systems include the Gemini family, Gemma open models, Veo video generation, Lyria music generation, Gemini Robotics, and AI systems for scientific discovery. The site also publishes research and provides access to models through products and developer platforms such as Google AI Studio, the Gemini API, and related enterprise tools.

DeepJIT is a lightweight, header-only C++20 library for just-in-time compilation, caching, loading, and launching of device kernels on NVIDIA CUDA GPUs and Huawei Ascend NPUs. It provides a shared runtime interface for both backends while keeping kernel source and compiler options backend-specific. The runtime hashes kernel source, tracked includes, compiler information, effective options, and application-provided dependency signatures to reuse compiled artifacts through in-memory and on-disk caches. Cache directories can be shared across users, processes, and nodes on local or distributed filesystems, with completed entries published through atomic directory renames. Lazy initialization defers device and compiler discovery until first use. DeepJIT integrates with PyTorch CUDA and torch_npu streams and can expose a runtime through pybind11. The CUDA backend uses NVCC and the CUDA Driver API to produce, load, and launch CUBIN files; the Ascend backend uses Bisheng, ld.lld, and ACL to compile, link, load, and launch kernels. It supports per-kernel compiler and launch options, compilation diagnostics, and optional PTX, SASS, or Ascend assembly dumps. The host environment requires Linux, a C++20 compiler with std::format support, Python, pybind11, and the dependencies for the selected backend; it is intended to be embedded in another C++ or Python extension as a header-only dependency.