Vulkan: add the missing int32 -> uint8 view_convert variant

The view_convert combo lists generate uint8 -> int32 but not the reverse,
so a graph containing an int32 -> uint8 view_convert lowers cleanly and
then aborts at run time:

  Could not find ShaderInfo with name view_convert_buffer_int32_uint8
  (ShaderRegistry.cpp:54, (it != listings_.end()) is false)

The partitioner has no visibility into which dtype pairs were generated,
so this surfaces as a crash on device rather than the node being left on
host. sentence-transformers/all-MiniLM-L6-v2 hits it through its
attention mask on any graph lowered with VulkanPartitioner.

view_convert is a plain elementwise OUT_T(in) cast, so the pair needs
nothing beyond being listed. Verified on a Galaxy S26 Ultra (Adreno 840):
with this variant generated, all-MiniLM-L6-v2 runs and its embedding
matches the eager reference to cosine 0.99999726 (max abs deviation
4.0e-04), bit-identical across 90 in-process replays.

Author: msluszniak

backends/vulkan/runtime/graph/ops/glsl/view_convert_buffer.yaml

@@ -18,6 +18,7 @@ view_convert_buffer:
         - parameter_values: [uint8, float]
         - parameter_values: [uint8, half]
         - parameter_values: [uint8, int32]
+        - parameter_values: [int32, uint8]
         - parameter_values: [float, int32]
         - parameter_values: [float, half]
         - parameter_values: [half, float]

backends/vulkan/runtime/graph/ops/glsl/view_convert_texture.yaml

@@ -18,6 +18,7 @@ view_convert_texture:
         - parameter_values: [uint8, float]
         - parameter_values: [uint8, half]
         - parameter_values: [uint8, int32]
+        - parameter_values: [int32, uint8]
         - parameter_values: [float, int32]
         - parameter_values: [float, half]
         - parameter_values: [half, float]