Sign in

Repository Index

47,133 repositories indexed

Filters (1)

Filters

Clear all filters

1–21 of 21 · Most stars

Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.

A self-hosted tool for automatically patching and distributing Android packages, built on Morphe Desktop.

Fish Audio Drama 3 text-to-speech on the TensorFold native CUDA engine for DGX Spark (GB10): recipe, engine patches, benchmarks. Built with Fish Audio.