paragontasx/ferro

Native OpenCL inference engine for Intel N100-class SoCs: EmbeddingGemma-2, LiquidAI d1-omni and LFM2.5 chat in one C++ binary, on the iGPU. Measured ~2x llama.cpp's own Vulkan backend on the same N100 (2.1-2.3x); OpenAI-compatible server, CPU fallback, bit-exact batch invariance.

语言：C++ · GitHub 星标：9 · Fork：0

话题：c-plus-plus · decision-models · embeddings · gguf · inference · intel-n100 · llama-cpp · llm

在 GitHub 上查看原仓库