v0.40.1

See https://github.com/quic/ai-hub-models/releases/v0.40.1 for changelog.

README.md

@@ -45,8 +45,6 @@ More details on model performance across various devices, can be found
 | text_encoder | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 5.139 ms | 0 - 19 MB | NPU | Use Export Script |
 | text_encoder | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_CONTEXT_BINARY | 4.294 ms | 0 - 17 MB | NPU | Use Export Script |
 | text_encoder | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | PRECOMPILED_QNN_ONNX | 4.337 ms | 0 - 13 MB | NPU | Use Export Script |
-| text_encoder | w8a16 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | QNN_CONTEXT_BINARY | 11.611 ms | 0 - 14 MB | NPU | Use Export Script |
-| text_encoder | w8a16 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | PRECOMPILED_QNN_ONNX | 11.467 ms | 0 - 13 MB | NPU | Use Export Script |
 | text_encoder | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_CONTEXT_BINARY | 4.28 ms | 0 - 11 MB | NPU | Use Export Script |
 | text_encoder | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | PRECOMPILED_QNN_ONNX | 4.251 ms | 0 - 14 MB | NPU | Use Export Script |
 | text_encoder | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 8.291 ms | 0 - 0 MB | NPU | Use Export Script |
@@ -63,8 +61,6 @@ More details on model performance across various devices, can be found
 | unet | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 68.651 ms | 0 - 16 MB | NPU | Use Export Script |
 | unet | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_CONTEXT_BINARY | 54.913 ms | 0 - 14 MB | NPU | Use Export Script |
 | unet | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | PRECOMPILED_QNN_ONNX | 55.953 ms | 0 - 11 MB | NPU | Use Export Script |
-| unet | w8a16 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | QNN_CONTEXT_BINARY | 147.988 ms | 0 - 14 MB | NPU | Use Export Script |
-| unet | w8a16 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | PRECOMPILED_QNN_ONNX | 149.585 ms | 0 - 14 MB | NPU | Use Export Script |
 | unet | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_CONTEXT_BINARY | 42.594 ms | 0 - 11 MB | NPU | Use Export Script |
 | unet | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | PRECOMPILED_QNN_ONNX | 41.234 ms | 0 - 7 MB | NPU | Use Export Script |
 | unet | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 95.869 ms | 0 - 0 MB | NPU | Use Export Script |
@@ -81,8 +77,6 @@ More details on model performance across various devices, can be found
 | vae | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 161.857 ms | 3 - 22 MB | NPU | Use Export Script |
 | vae | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_CONTEXT_BINARY | 176.589 ms | 0 - 18 MB | NPU | Use Export Script |
 | vae | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | PRECOMPILED_QNN_ONNX | 145.862 ms | 3 - 17 MB | NPU | Use Export Script |
-| vae | w8a16 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | QNN_CONTEXT_BINARY | 511.206 ms | 0 - 14 MB | NPU | Use Export Script |
-| vae | w8a16 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | PRECOMPILED_QNN_ONNX | 444.926 ms | 3 - 17 MB | NPU | Use Export Script |
 | vae | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_CONTEXT_BINARY | 117.531 ms | 0 - 11 MB | NPU | Use Export Script |
 | vae | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | PRECOMPILED_QNN_ONNX | 92.037 ms | 3 - 14 MB | NPU | Use Export Script |
 | vae | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 264.316 ms | 0 - 0 MB | NPU | Use Export Script |

precompiled/qualcomm-snapdragon-7gen5/Stable-Diffusion-v2.1_text_encoder_w8a16.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:eb00021909a29cdca1cb93fc702f5565558186251b20c940a9e3ef47578355c1
-size 396083200

precompiled/qualcomm-snapdragon-7gen5/Stable-Diffusion-v2.1_text_encoder_w8a16.onnx.zip

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3c5702a1b80d980dd543357c59d0dd08e89191fde5f5ed7f50b93324b0867d38
-size 299405756

precompiled/qualcomm-snapdragon-7gen5/Stable-Diffusion-v2.1_unet_w8a16.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:96bc7914d415159081deae6a77dee920c00d5b681ca047776339653d84a54ca8
-size 884645888

precompiled/qualcomm-snapdragon-7gen5/Stable-Diffusion-v2.1_unet_w8a16.onnx.zip

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:26e6bd285933ceee1aacd36a1618888ca507cb9d17592d578c0edfdca36d82ab
-size 544309178

precompiled/qualcomm-snapdragon-7gen5/Stable-Diffusion-v2.1_vae_w8a16.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ad4827bbc147099be43f3f29011ea71a0682658a10684cae751b8ccb9782dbbc
-size 72851456

precompiled/qualcomm-snapdragon-7gen5/Stable-Diffusion-v2.1_vae_w8a16.onnx.zip

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bfc0c44992365eff7d115f57f6d8d3b679992428a78ebc62c4ecc9a537dbf7ad
-size 41143881

precompiled/qualcomm-snapdragon-7gen5/tool-versions.yaml

@@ -1,4 +0,0 @@
-tool_versions:
-  precompiled_qnn_onnx:
-    qairt: 2.37.1.250807093845_124904
-    onnx_runtime: 1.23.0