Stars
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than y…
GPU FDTD for photonics: browser CAD workbench, Python project API and Torch-differentiable simulations on CUDA
A high-throughput and memory-efficient inference and serving engine for LLMs