llama.cpp b10676 修复多批次卷积转置问题

AI 摘要

llama.cpp 发布 b10676 版本，修复了 conv_transpose_2d 在 CPU 和 Metal 后端中多批次处理的问题，确保所有批次正确计算。该修复解决了多批次输出为零的 bug，并增加了测试用例。

正文节选

<details open> ggml : fix conv_transpose_2d for multiple batches (#26132) * ggml : fix conv_transpose_2d for multiple batches ggml_compute_forward_conv_transpose_2d_impl only computed the first batch (ne[3] of the destination); every batch after the first was left as zero. Both the src1 permutation and the main compute loop now iterate over the batch dimension, and the work buffer size in ggml_graph_plan is scaled by the src1 batch count so the extra permuted batches fit. A multi-batch test c

发布时间：2026-08-29 02:01

抓取时间：2026-08-29 02:09

来源机构：ggml-org