llama.cpp optimized for NVIDIA Tesla V100 (SM70). Qwen3.8-Flash-Next (MoE) with MTP on 1/2/3/6x V100-16GB at 262K context (6 GPUs: prefill 3402 tok/s at 200K; 2 GPUs on one socket: 2152 tok/s). Qwen3.8-27B with DFlash2 on 1-6 GPUs, up to 512K context. Multimodal, thinking, concurrent serving, built-in web UI.
One line of NInfer for the Blackwell, Ada Lovelace, Ampere, Turing and Volta NVIDIA GPUs, consolidated from the forks that carry it: GGUF block formats, ternary Bonsai 2, device route profiles, MTP and DFlash2.