llama.cpp

b37124d2 - vulkan: handle quantize_q8_1 overflowing the max workgroup count (#18515)

vulkan: handle quantize_q8_1 overflowing the max workgroup count (#18515) * vulkan: handle quantize_q8_1 overflowing the max workgroup count * vulkan: Fix small tile size matmul on lavapipe * fix mul_mat_id failures