llama.cpp b10782 发布：修复多 GPU CUDA 并发流问题

AI 摘要

llama.cpp 发布 b10782 版本，主要修复了多 GPU 场景下 CUDA 图优化被跳过的问题，通过显式设置设备允许每个分片并发流。该版本提供了适用于多种平台和硬件的二进制文件，包括 macOS、Linux、Windows、Android 等。

正文节选

<details open> CUDA: Allow concurrent streams per split for multi-GPU (#28198) * CUDA: Allow CUDA optimization per split for multi-GPU. Previous guard caused multi-GPU to skip the graph optimization. The graph is already split per device and the optimization doesnt run over the whole model but once per split, and thus should be allowed. However, the CUDA event ggml_cuda_concurrent_event belongs to whichever GPU was "current" when created. If the pass ran while GPU 0 was current, it would sti

发布时间：2026-09-03 18:26

抓取时间：2026-09-03 18:45

来源机构：ggml-org