Popular repositories Loading

1. llama-cpp-turboquant llama-cpp-turboquant Public

   llama.cpp fork with TurboQuant quantization (turbo2/3/4) and TriAttention GPU-accelerated KV cache pruning. 75 tok/s on Qwen3-8B / RTX 3080.

   C++ 57 12

2. godzilla-llama.cpp godzilla-llama.cpp Public

   MSVC+CUDA llama.cpp fork for Windows: KDA/GDN, long-context KV placement, TurboQuant/TCQ when measured, speculative draft. Lab defaults — TriAttention opt-in only, not recommended.

   C++ 8 1

3. FreeToken FreeToken Public

   Forked from FlashML-org/FreeToken

   Python 5

4. JellyRancher JellyRancher Public

   PyQt6-based media library management application with Jellyfin integration, LLM-powered analysis, and comprehensive metadata handling

   Python 1

5. eagledb eagledb Public

   An embeddable, in-process T-SQL query engine powered by Apache DataFusion. Run SQL Server queries locally against in-memory Arrow tables — hundreds of times faster than T-SQL against the production…

   Rust 1

6. ac7ultrawide ac7ultrawide Public

   Runtime ultrawide fix for ACE COMBAT 7: SKIES UNKNOWN — removes black bars, fixes FOV, and updates HUD shift

   C++ 1