Add XNNPACK int8 exports

README.md

@@ -17,9 +17,27 @@ Upstream model: [FastSAM](https://docs.ultralytics.com/models/fast-sam/)
 | Path | Backend | Precision |
 | --- | --- | --- |
 | `s/coreml/fast_sam_s_coreml_fp16.pte` | coreml | fp16 |
+| `s/vulkan/fast_sam_s_vulkan_fp16.pte` | vulkan | fp16 |
 | `s/xnnpack/fast_sam_s_xnnpack_fp32.pte` | xnnpack | fp32 |
+| `s/xnnpack/fast_sam_s_xnnpack_int8.pte` | xnnpack | int8 |
 | `x/coreml/fast_sam_x_coreml_fp16.pte` | coreml | fp16 |
+| `x/vulkan/fast_sam_x_vulkan_fp16.pte` | vulkan | fp16 |
 | `x/xnnpack/fast_sam_x_xnnpack_fp32.pte` | xnnpack | fp32 |
+| `x/xnnpack/fast_sam_x_xnnpack_int8.pte` | xnnpack | int8 |
+
+## XNNPACK int8
+
+The `xnnpack/*_int8.pte` files are static int8 (PT2E, per-channel weights) with the
+first convolution and the Segment head kept fp32, except the mask prototype branch.
+Class-agnostic COCO AR@100 on the first 500 val2017 images (all categories merged,
+box NMS at IoU 0.9 as in the library):
+
+| | box AR@100 | mask AR@100 |
+| --- | --- | --- |
+| s fp32 | 41.65 | 36.25 |
+| s int8 | 41.81 | 36.13 |
+| x fp32 | 46.07 | 40.93 |
+| x int8 | 46.09 | 41.04 |
 
 ## Unshipped backends
 
@@ -36,13 +54,19 @@ config.json                            30 B
 s/coreml/config.json                   1.2 kB
 s/coreml/fast_sam_s_coreml_fp16.pte    23.1 MB
 s/mlx/NOTES.md                         2.0 kB
-s/xnnpack/config.json                  1.2 kB
+s/vulkan/config.json                   1.3 kB
+s/vulkan/fast_sam_s_vulkan_fp16.pte    22.6 MB
+s/xnnpack/config.json                  2.1 kB
 s/xnnpack/fast_sam_s_xnnpack_fp32.pte  45.2 MB
+s/xnnpack/fast_sam_s_xnnpack_int8.pte  18.5 MB
 x/coreml/config.json                   1.2 kB
 x/coreml/fast_sam_x_coreml_fp16.pte    139 MB
 x/mlx/NOTES.md                         2.0 kB
-x/xnnpack/config.json                  1.2 kB
+x/vulkan/config.json                   1.3 kB
+x/vulkan/fast_sam_x_vulkan_fp16.pte    138 MB
+x/xnnpack/config.json                  2.1 kB
 x/xnnpack/fast_sam_x_xnnpack_fp32.pte  276 MB
+x/xnnpack/fast_sam_x_xnnpack_int8.pte  99.6 MB
 ```
 
 ## Compatibility

s/xnnpack/config.json

@@ -55,6 +55,53 @@
           ]
         }
       }
+    },
+    {
+      "file": "fast_sam_s_xnnpack_int8.pte",
+      "precision": "int8",
+      "size": "s",
+      "methods": {
+        "forward": {
+          "inputs": [
+            {
+              "shape": [
+                1,
+                3,
+                640,
+                640
+              ],
+              "dtype": "float32"
+            }
+          ],
+          "outputs": [
+            {
+              "shape": [
+                1,
+                300,
+                4
+              ],
+              "dtype": "float32"
+            },
+            {
+              "shape": [
+                1,
+                300,
+                32
+              ],
+              "dtype": "float32"
+            },
+            {
+              "shape": [
+                1,
+                32,
+                160,
+                160
+              ],
+              "dtype": "float32"
+            }
+          ]
+        }
+      }
     }
   ]
 }

s/xnnpack/fast_sam_s_xnnpack_int8.pte

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fab58acb6d29c6e310528e3c81c7eff51ae93dcf12ebf32578b73a591358e89
+size 19346816

x/xnnpack/config.json

@@ -55,6 +55,53 @@
           ]
         }
       }
+    },
+    {
+      "file": "fast_sam_x_xnnpack_int8.pte",
+      "precision": "int8",
+      "size": "x",
+      "methods": {
+        "forward": {
+          "inputs": [
+            {
+              "shape": [
+                1,
+                3,
+                640,
+                640
+              ],
+              "dtype": "float32"
+            }
+          ],
+          "outputs": [
+            {
+              "shape": [
+                1,
+                300,
+                4
+              ],
+              "dtype": "float32"
+            },
+            {
+              "shape": [
+                1,
+                300,
+                32
+              ],
+              "dtype": "float32"
+            },
+            {
+              "shape": [
+                1,
+                32,
+                160,
+                160
+              ],
+              "dtype": "float32"
+            }
+          ]
+        }
+      }
     }
   ]
 }

x/xnnpack/fast_sam_x_xnnpack_int8.pte

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcd82ab54de24bb53919c3f9c37585a62e53a70635ff6791a3b61ca36364aa0f
+size 104428800