vulkan: Fuse rope+set_rows

[jeffbolznv]

This pattern appears in a lot of models, the rope operation is applied right before storing into the KV cache (usually on the K tensor).

Add a path to some of the rope shaders that computes the destination address based on the set_rows tensor. Compile variants of the shader with D_TYPE of f16 (the usual KV cache type).

Add a src3 operand to ggml_vk_op_f32 - sometimes rope uses three srcs and needs the fourth for the row indices.

Add fused_ops_write_mask to indicate which intermediate tensors need to write their results to memory. Skipping writing the roped K value helps to allow more nodes to run concurrently.

Add logic to ggml_vk_graph_optimize to make ROPE+VIEW+SET_ROWS consecutive. It rarely starts out that way in the graph.

Add new backend tests.

My test system has been giving less stable results today, so here's just one from llama2, but this helps quite a few models.

before:
| llama 7B Q4_0                  |   3.56 GiB |     6.74 B | Vulkan     |  99 |  1 |           tg128 |        269.90 ± 1.69 |

after:
| llama 7B Q4_0                  |   3.56 GiB |     6.74 B | Vulkan     |  99 |  1 |           tg128 |        275.67 ± 0.76 |