🌍 Live Open Source Explorer
Explore live open-source projects and AI models.
Search public open-source repositories from GitHub and AI models from Hugging Face. Every page shows 10 results with clean pagination.
🔎 Live Search
Search live open-source data
Search GitHub repositories and Hugging Face models directly, then explore stars, downloads, source links and project details.
Live Results
GitHub Open Source Repositories
Search: dflash-mlx
Page 1
Showing 6 results from 6
bstnxbt/dflash-mlx
GitHub Python Apache License 2.0Lossless DFlash speculative decoding for MLX on Apple Silicon
External source
GitHub
Aryagm/dflash-mlx
GitHub Python MIT LicenseExact speculative decoding on Apple Silicon, powered by MLX.
External source
GitHub
humanrouter/ddtree-mlx
GitHub PythonTree-based speculative decoding for Apple Silicon (MLX). ~10-15% faster than DFlash on code, ~1.5x over autoregressive. First MLX port with custom Metal kernels for hybrid model support.
External source
GitHub
0xClandestine/mirror-sd
GitHub PythonDFlash block-diffusion speculative decoding running on Apple Silicon via MLX, with an ANE execution path that explores heterogeneous accelerator dispatch.
External source
GitHub
cryptopoly/ChaosEngineAI
GitHub Python Apache License 2.0Local AI workstation — discover, run, chat, benchmark, and generate images from open-weight models. DFlash/DDTree speculative decoding, TurboQuant & TriAttention cache compression strategies, MLX + llama.cpp + vLLM + MTPLX backends.
External source
GitHub
eauchs/mlx-dflash
GitHub Python3.34× faster inference on Apple Silicon — native MLX port of DFlash speculative decoding
External source
GitHub