Pinned Loading

1. gemma4_jinja gemma4_jinja Public

   Custom Gemma 4 chat template for llama.cpp/OpenWebUI that preserves tool-calling behavior while preventing thinking-channel (<|channel>thought) leakage in outputs.

   Jinja 14 2

2. libstrix libstrix Public

   Fast vLLM on AMD Strix Halo: one docker command for Qwen, Gemma, LFM and more, up to 31x faster prefill and ~2x decode vs stock vLLM at long context.

   Python 21 1

3. strix-llama.cpp strix-llama.cpp Public

   Forked from halo-box/strix-llama.cpp

   LLM inference in C/C++

   C++ 3