tac0mania/taco
GPT-2 with zero floats: compress on a Mac, decompress on Windows/CUDA/Vulkan, byte-for-byte identical. Lossless LLM compression that doesn't break when the hardware changes. (alpha)
GitHub repository with 11 stars and 1 forks.
Language: Rust
Topics: compression, cross-platform, cuda, deterministic, gpt-2, integer-arithmetic, llm, lossless-compression, rust, webgpu