Hugging Face's logo

qualcomm
/
ConvNext-Base

Image Classification
PyTorch
LiteRT
bu_auto
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
3ff88d9
·
verified ·
1 Parent(s): e5917c1

v0.34.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.34.0 for changelog.

Files changed (6) hide show
  1. ConvNext-Base_w8a16.dlc +1 -1
  2. README.md +18 -27
  3. precompiled/qualcomm-qcs6490-proxy/sdk_versions.yml +3 -0
  4. precompiled/qualcomm-snapdragon-x-elite/ConvNext-Base.onnx.zip +2 -2
  5. precompiled/qualcomm-snapdragon-x-elite/ConvNext-Base_w8a16.onnx.zip +2 -2
  6. precompiled/qualcomm-snapdragon-x-elite/sdk_versions.yml +5 -0
ConvNext-Base_w8a16.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d815f7496411d92ef52367e12dc559470cc92df5c445e1f5a27d9bb8dd2053f
3
  size 93041675
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acc5f20429b1235aa20ddf416b15fb8d93d02468a8ff426a82d6579b0e848075
3
  size 93041675
README.md CHANGED
@@ -23,6 +23,7 @@ More details on model performance across various devices, can be found
23
  [here](https://aihub.qualcomm.com/models/convnext_base).
24
 
25
 
 
26
  ### Model Details
27
 
28
  - **Model Type:** Model_use_case.image_classification
@@ -35,37 +36,37 @@ More details on model performance across various devices, can be found
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
- | ConvNext-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 41.584 ms | 0 - 283 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
39
  | ConvNext-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 42.312 ms | 1 - 281 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
40
- | ConvNext-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 18.282 ms | 0 - 295 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
41
  | ConvNext-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 20.47 ms | 0 - 300 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
42
- | ConvNext-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 7.451 ms | 0 - 28 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
43
  | ConvNext-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 8.253 ms | 0 - 28 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
44
- | ConvNext-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 11.422 ms | 0 - 284 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
45
  | ConvNext-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 12.128 ms | 1 - 281 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
46
- | ConvNext-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 7.483 ms | 0 - 34 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
47
  | ConvNext-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 8.283 ms | 0 - 25 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
48
  | ConvNext-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 7.51 ms | 1 - 22 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
49
- | ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.561 ms | 0 - 295 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
50
  | ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 6.003 ms | 1 - 290 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
51
  | ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.498 ms | 1 - 295 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
52
- | ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 4.839 ms | 0 - 282 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
53
  | ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 5.395 ms | 1 - 286 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
54
  | ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 4.427 ms | 0 - 283 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
55
  | ConvNext-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 8.87 ms | 1390 - 1390 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
56
  | ConvNext-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 7.938 ms | 176 - 176 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
57
- | ConvNext-Base | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 14.436 ms | 0 - 129 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
58
- | ConvNext-Base | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 9.323 ms | 0 - 143 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
59
- | ConvNext-Base | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 5.979 ms | 0 - 33 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
60
- | ConvNext-Base | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 6.226 ms | 0 - 130 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
61
- | ConvNext-Base | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 39.643 ms | 0 - 207 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
62
- | ConvNext-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 5.96 ms | 0 - 32 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
63
  | ConvNext-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 234.724 ms | 628 - 815 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx) |
64
- | ConvNext-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 4.141 ms | 0 - 137 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
65
  | ConvNext-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 179.103 ms | 653 - 1431 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx) |
66
- | ConvNext-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 3.294 ms | 0 - 130 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
67
  | ConvNext-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 155.127 ms | 689 - 1378 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx) |
68
- | ConvNext-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 6.624 ms | 481 - 481 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
69
  | ConvNext-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 224.865 ms | 922 - 922 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx) |
70
 
71
 
@@ -124,17 +125,7 @@ device. This script does the following:
124
  ```bash
125
  python -m qai_hub_models.models.convnext_base.export
126
  ```
127
- ```
128
- Profiling Results
129
- ------------------------------------------------------------
130
- ConvNext-Base
131
- Device : cs_8275 (ANDROID 14)
132
- Runtime : TFLITE
133
- Estimated inference time (ms) : 41.6
134
- Estimated peak memory usage (MB): [0, 283]
135
- Total # Ops : 598
136
- Compute Unit(s) : npu (598 ops) gpu (0 ops) cpu (0 ops)
137
- ```
138
 
139
 
140
  ## How does this work?
 
23
  [here](https://aihub.qualcomm.com/models/convnext_base).
24
 
25
 
26
+
27
  ### Model Details
28
 
29
  - **Model Type:** Model_use_case.image_classification
 
36
 
37
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
+ | ConvNext-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 41.615 ms | 0 - 283 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
40
  | ConvNext-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 42.312 ms | 1 - 281 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
41
+ | ConvNext-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 18.213 ms | 0 - 296 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
42
  | ConvNext-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 20.47 ms | 0 - 300 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
43
+ | ConvNext-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 7.393 ms | 0 - 19 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
44
  | ConvNext-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 8.253 ms | 0 - 28 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
45
+ | ConvNext-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 11.421 ms | 0 - 283 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
46
  | ConvNext-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 12.128 ms | 1 - 281 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
47
+ | ConvNext-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 7.444 ms | 0 - 31 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
48
  | ConvNext-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 8.283 ms | 0 - 25 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
49
  | ConvNext-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 7.51 ms | 1 - 22 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
50
+ | ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.545 ms | 0 - 294 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
51
  | ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 6.003 ms | 1 - 290 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
52
  | ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.498 ms | 1 - 295 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
53
+ | ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 4.833 ms | 0 - 283 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
54
  | ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 5.395 ms | 1 - 286 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
55
  | ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 4.427 ms | 0 - 283 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
56
  | ConvNext-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 8.87 ms | 1390 - 1390 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
57
  | ConvNext-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 7.938 ms | 176 - 176 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx) |
58
+ | ConvNext-Base | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 14.454 ms | 0 - 130 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
59
+ | ConvNext-Base | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 8.993 ms | 0 - 144 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
60
+ | ConvNext-Base | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 5.992 ms | 0 - 34 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
61
+ | ConvNext-Base | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 6.265 ms | 0 - 130 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
62
+ | ConvNext-Base | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 39.607 ms | 0 - 207 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
63
+ | ConvNext-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 5.953 ms | 0 - 33 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
64
  | ConvNext-Base | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 234.724 ms | 628 - 815 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx) |
65
+ | ConvNext-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 4.155 ms | 0 - 141 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
66
  | ConvNext-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 179.103 ms | 653 - 1431 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx) |
67
+ | ConvNext-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 3.823 ms | 0 - 130 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
68
  | ConvNext-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 155.127 ms | 689 - 1378 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx) |
69
+ | ConvNext-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 6.624 ms | 460 - 460 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
70
  | ConvNext-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 224.865 ms | 922 - 922 MB | NPU | [ConvNext-Base.onnx](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx) |
71
 
72
 
 
125
  ```bash
126
  python -m qai_hub_models.models.convnext_base.export
127
  ```
128
+
 
 
 
 
 
 
 
 
 
 
129
 
130
 
131
  ## How does this work?
precompiled/qualcomm-qcs6490-proxy/sdk_versions.yml ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
precompiled/qualcomm-snapdragon-x-elite/ConvNext-Base.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b18a71d76f574ff5e9d24f01b586d1dd83ac648633ba70473eb5c927b7e4a835
3
- size 165950089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa0f2f3a9881360a89a9c80f99d4391b28b166832896d1bb52d5783cd0586e86
3
+ size 165950096
precompiled/qualcomm-snapdragon-x-elite/ConvNext-Base_w8a16.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95945a95a89922a5762d7a3084961d8628d4237c8875eb98f484dcc63a67697c
3
- size 81386169
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73a3b2ed6c80287785128b29a03685ab1d29184d97063cc78aaf19e18915199a
3
+ size 81386171
precompiled/qualcomm-snapdragon-x-elite/sdk_versions.yml ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
4
+ precompiled_qnn_onnx:
5
+ qairt: 2.33.2.250410134701_117956