Popular repositories Loading

1. llama-cpp-mtp-turboquant-sm120-blackwell-windows llama-cpp-mtp-turboquant-sm120-blackwell-windows Public

   Windows prebuilt of llama.cpp combining Multi-Token Prediction (MTP) + TurboQuant KV cache compression + native sm_120 (Blackwell consumer GPU, FP4 tensor cores). For RTX 5060 Ti / 5070 / 5080 / 5090.

   15 4

2. beellama.cpp beellama.cpp Public

   Forked from Anbeeld/beellama.cpp

   DFlash & TurboQuant in llama.cpp with up to 3x faster generation and 7.5x more KV cache in same VRAM

   C++ 3

3. strata-flint strata-flint Public

   High-performance native C++/CUDA inference engine for Flint 40B Preview MoE (256 experts). Batched Tensor Core prefill (1,238 tok/s), CUDA Graph decode (90 tok/s), 3-tier sliding KV cache (256K con…

   C++ 1

4. weatherland weatherland Public

   Weatherland — live desktop wallpaper for Windows. Product page and privacy policy.

   HTML

5. ai-product-card ai-product-card Public

   Прототип сервиса: черновики карточек товаров для B2B-каталога КИП на FastAPI + LLM

   Python

6. Strata Strata Public

   Forked from Niko1221/Strata

   Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.

   C++