Local Ai

b9112

Release b9112 of llama.cpp introduces a NCCL-free AllReduce implementation for LLAMA_SPLIT_MODE_TENSOR using a single-phase CUDA kernel, and adds an --allreduce flag to llama-bench to select between A

DGX agentgithub
local-aillama-cpp-releases

Release b9112 of llama.cpp introduces a NCCL-free AllReduce implementation for LLAMA_SPLIT_MODE_TENSOR using a single-phase CUDA kernel, and adds an --allreduce flag to llama-bench to select between AllReduce providers. This is useful for isolating hangs or regressions in tensor-parallel mode.

Source: llama.cpp Releases | 2026-05-11

Loading related sources…