Add the Vulkan fp32 export

Android GPU build of all-MiniLM-L6-v2. 2.4x faster than the XNNPACK build on a Mali-G76 at the published 254 token shape (169.8 ms against 408.4 ms median), bit-identical across 10 executions, cosine 0.9999924 against the CPU reference.

.gitattributes

@@ -38,3 +38,4 @@ all-MiniLM-L6-v2_xnnpack.pte filter=lfs diff=lfs merge=lfs -text
 xnnpack/all_minilm_l6_v2_xnnpack_fp32.pte filter=lfs diff=lfs merge=lfs -text
 coreml/all_minilm_l6_v2_coreml_fp16.pte filter=lfs diff=lfs merge=lfs -text
 coreml/all_minilm_l6_v2_coreml_fp32.pte filter=lfs diff=lfs merge=lfs -text
+vulkan/all_minilm_l6_v2_vulkan_fp32.pte filter=lfs diff=lfs merge=lfs -text

vulkan/all_minilm_l6_v2_vulkan_fp32.pte

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5885b4d342315c154466e2379575d9ea7683310081319356ddc0659a0075b826
+size 90343684

vulkan/config.json

@@ -0,0 +1,47 @@
+{
+  "$schema": "https://huggingface.co/software-mansion/react-native-executorch-spec/resolve/main/config.schema.json",
+  "model": "all_minilm_l6_v2",
+  "family": "sbert",
+  "capabilities": [
+    "text-embedding"
+  ],
+  "backend": "vulkan",
+  "license": "apache-2.0",
+  "variants": [
+    {
+      "file": "all_minilm_l6_v2_vulkan_fp32.pte",
+      "precision": "fp32",
+      "quantized": false,
+      "default": true,
+      "methods": {
+        "forward": {
+          "inputs": [
+            {
+              "shape": [
+                1,
+                254
+              ],
+              "dtype": "int64"
+            },
+            {
+              "shape": [
+                1,
+                254
+              ],
+              "dtype": "int64"
+            }
+          ],
+          "outputs": [
+            {
+              "shape": [
+                1,
+                384
+              ],
+              "dtype": "float32"
+            }
+          ]
+        }
+      }
+    }
+  ]
+}