ggml-org/llama.cpp b11523

on GitHub

ci: fix Models Backend webgpu by supporting GGML_OP_DUP (#30216)

The mixed batch path of PR-29622 writes the token rows with set_rows
into a dup of the embeddings. WebGPU did not support DUP, so the dup
ran on the CPU while the set_rows writing into it was scheduled on
WebGPU, which then bound a CPU buffer and crashed. DUP is the same copy
as CPY and CONT and now goes through the same path.