TensorFold

AlphaFold is an open-source implementation of the AlphaFold v2 protein-structure prediction inference pipeline, developed by Google DeepMind. The repository also includes an implementation of AlphaFold-Multimer for predicting protein complexes and documents the updated AlphaFold v2.3.0 models and inference procedure. It runs on Linux using Docker and a modern NVIDIA GPU, with model parameters and genetic databases supplied separately; the full database setup requires substantial storage.

TensorFlow is an open-source, end-to-end machine-learning platform originally developed by Google Brain. It provides tools, libraries, community resources, and stable Python and C++ APIs for building, training, and deploying machine-learning applications, with support for CPU and GPU execution and additional device plugins. In TensorFlow-based deployment stacks, it provides serving infrastructure and the SavedModel format; JAX graphs can be converted to SavedModel for integration with TensorFlow serving. The project is distributed through PyPI packages, Docker containers, and source builds, including CPU-only and nightly packages.

KTransformers is an open-source research framework for efficient large-language-model inference and fine-tuning through heterogeneous CPU-GPU computing. Its user-facing capabilities are provided through the kt-kernel source tree: high-performance inference and supervised fine-tuning (SFT). For mixture-of-experts models, it uses heterogeneous expert scheduling, placing frequently used or “hot” experts on GPUs and other experts on CPUs with optimized AMX, AVX512, or AVX2 kernels and NUMA-aware memory management. It supports CPU-side INT4/INT8 quantized weights, GPU-side GPTQ, native BF16 and FP8 precision, and multiple CPU, GPU, and NPU backends. The SFT capability integrates with LlamaFactory for hybrid CPU-GPU fine-tuning of large MoE models, including LoRA and full-parameter training, with INT4/INT8 quantization options.

Lithos Metal is an open-source LLM inference engine for Apple silicon that generates specialized Metal megakernels and serves models locally for coding agents and other applications. Its compiler decomposes operators into matrix tiles, attention partitions, and recurrent-state slices, records their dependencies, and generates layer-wise fused GPU tasks. The runtime combines mixer megakernels, GPU-resident generation control, pre-encoded Metal indirect command buffers, and DSpark speculative decoding, in which a target-conditioned draft proposes token blocks and the target model verifies and commits the accepted prefix. The server provides OpenAI-compatible Chat Completions and Responses adapters plus an Anthropic Messages adapter, with text generation, tool calls, and SSE streaming; launchers configure clients including OpenCode, Claude Code, Codex, and Hermes. It runs on Apple silicon with macOS 26 or later, is distributed through a Lithos Homebrew tap or source installation, and is licensed under Apache 2.0.

FreeToken is an edge-native Mixture-of-Experts (MoE) serving engine for running open-weight, frontier-scale models on consumer hardware. It treats GPUs, CPUs, host memory, and interconnects as a unified inference platform, using bandwidth-adaptive CPU–GPU co-execution, double-buffered prefill streaming, global LRU expert caching, graph-compatible execution, and the FTW fast weight format. Semantic anchor checkpoints let recurrent state and KV caches survive agentic context edits without redundant recomputation, while runtime VRAM reallocation moves memory between expert caches and KV storage without restarting the engine or reloading weights. FreeToken supports multiple MoE models, quantization formats, and Anthropic- and OpenAI-compatible APIs, and is distributed as a Windows or Linux desktop application and as a Python/CLI package. The project is released under the Apache License 2.0.