llama.cpp

e82f9e2b - [SYCL] Fix batched impl for NVidia GPU (#6164)

[SYCL] Fix batched impl for NVidia GPU (#6164) * Fix batched impl * Maintain previous behaviour for igpu * retrigger CI --------- Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>