Hugging Face's logo

qualcomm
/
EfficientNet-B4

Image Classification
PyTorch
LiteRT
backbone
bu_auto
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
3e0b564
·
verified ·
1 Parent(s): df97f12

v0.34.0

Browse files

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

Files changed (7) hide show
  1. EfficientNet-B4_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/EfficientNet-B4.bin +1 -1
  5. precompiled/qualcomm-snapdragon-x-elite/EfficientNet-B4.onnx.zip +2 -2
  6. precompiled/qualcomm-snapdragon-x-elite/EfficientNet-B4_w8a16.onnx.zip +2 -2
  7. precompiled/qualcomm-snapdragon-x-elite/sdk_versions.yml +5 -0
EfficientNet-B4_w8a16.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a20a03cb780e8da54d87d18ba39b9a546f02bc12af75e710f314858b9cb758f5
3
  size 25214079
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96bc6807afcfef02991c9dbfc30734d20bb1d575e2b6c60e6664995a644fdebc
3
  size 25214079
README.md CHANGED
@@ -24,6 +24,7 @@ More details on model performance across various devices, can be found
24
  [here](https://aihub.qualcomm.com/models/efficientnet_b4).
25
 
26
 
 
27
  ### Model Details
28
 
29
  - **Model Type:** Model_use_case.image_classification
@@ -36,34 +37,34 @@ More details on model performance across various devices, can be found
36
 
37
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
- | EfficientNet-B4 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 12.19 ms | 0 - 67 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
40
  | EfficientNet-B4 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 11.889 ms | 1 - 33 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
41
- | EfficientNet-B4 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 6.983 ms | 0 - 87 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
42
  | EfficientNet-B4 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 7.723 ms | 1 - 47 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
43
- | EfficientNet-B4 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 3.309 ms | 0 - 422 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
44
  | EfficientNet-B4 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 3.215 ms | 1 - 48 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
45
- | EfficientNet-B4 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 4.371 ms | 0 - 66 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
46
  | EfficientNet-B4 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 4.212 ms | 1 - 33 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
47
- | EfficientNet-B4 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 3.314 ms | 0 - 421 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
48
  | EfficientNet-B4 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 3.183 ms | 0 - 64 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
49
  | EfficientNet-B4 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 3.191 ms | 1 - 129 MB | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
50
- | EfficientNet-B4 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 2.447 ms | 0 - 84 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
51
  | EfficientNet-B4 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 2.356 ms | 1 - 47 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
52
  | EfficientNet-B4 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 2.395 ms | 0 - 47 MB | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
53
- | EfficientNet-B4 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 2.333 ms | 0 - 71 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
54
  | EfficientNet-B4 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 2.176 ms | 1 - 38 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
55
  | EfficientNet-B4 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 1.941 ms | 1 - 38 MB | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
56
  | EfficientNet-B4 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 3.896 ms | 245 - 245 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
57
  | EfficientNet-B4 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 3.448 ms | 46 - 46 MB | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
58
- | EfficientNet-B4 | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 6.5 ms | 0 - 56 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
59
- | EfficientNet-B4 | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 4.186 ms | 0 - 73 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
60
- | EfficientNet-B4 | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 3.417 ms | 0 - 17 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
61
- | EfficientNet-B4 | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 3.834 ms | 0 - 56 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
62
- | EfficientNet-B4 | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 11.84 ms | 0 - 72 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
63
- | EfficientNet-B4 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 3.426 ms | 0 - 17 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
64
- | EfficientNet-B4 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 2.277 ms | 0 - 79 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
65
- | EfficientNet-B4 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 1.947 ms | 0 - 61 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
66
- | EfficientNet-B4 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 3.884 ms | 101 - 101 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
67
 
68
 
69
 
@@ -121,17 +122,7 @@ device. This script does the following:
121
  ```bash
122
  python -m qai_hub_models.models.efficientnet_b4.export
123
  ```
124
- ```
125
- Profiling Results
126
- ------------------------------------------------------------
127
- EfficientNet-B4
128
- Device : cs_8275 (ANDROID 14)
129
- Runtime : TFLITE
130
- Estimated inference time (ms) : 12.2
131
- Estimated peak memory usage (MB): [0, 67]
132
- Total # Ops : 482
133
- Compute Unit(s) : npu (482 ops) gpu (0 ops) cpu (0 ops)
134
- ```
135
 
136
 
137
  ## How does this work?
 
24
  [here](https://aihub.qualcomm.com/models/efficientnet_b4).
25
 
26
 
27
+
28
  ### Model Details
29
 
30
  - **Model Type:** Model_use_case.image_classification
 
37
 
38
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
+ | EfficientNet-B4 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 12.203 ms | 0 - 67 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
41
  | EfficientNet-B4 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 11.889 ms | 1 - 33 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
42
+ | EfficientNet-B4 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 6.972 ms | 0 - 87 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
43
  | EfficientNet-B4 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 7.723 ms | 1 - 47 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
44
+ | EfficientNet-B4 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 3.327 ms | 0 - 425 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
45
  | EfficientNet-B4 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 3.215 ms | 1 - 48 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
46
+ | EfficientNet-B4 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 4.354 ms | 0 - 66 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
47
  | EfficientNet-B4 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 4.212 ms | 1 - 33 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
48
+ | EfficientNet-B4 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 3.325 ms | 0 - 416 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
49
  | EfficientNet-B4 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 3.183 ms | 0 - 64 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
50
  | EfficientNet-B4 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 3.191 ms | 1 - 129 MB | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
51
+ | EfficientNet-B4 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 2.443 ms | 0 - 85 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
52
  | EfficientNet-B4 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 2.356 ms | 1 - 47 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
53
  | EfficientNet-B4 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 2.395 ms | 0 - 47 MB | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
54
+ | EfficientNet-B4 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 2.336 ms | 0 - 70 MB | NPU | [EfficientNet-B4.tflite](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.tflite) |
55
  | EfficientNet-B4 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 2.176 ms | 1 - 38 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
56
  | EfficientNet-B4 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 1.941 ms | 1 - 38 MB | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
57
  | EfficientNet-B4 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 3.896 ms | 245 - 245 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.dlc) |
58
  | EfficientNet-B4 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 3.448 ms | 46 - 46 MB | NPU | [EfficientNet-B4.onnx](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4.onnx) |
59
+ | EfficientNet-B4 | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 6.497 ms | 0 - 56 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
60
+ | EfficientNet-B4 | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 4.116 ms | 0 - 66 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
61
+ | EfficientNet-B4 | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 3.438 ms | 0 - 20 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
62
+ | EfficientNet-B4 | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 3.847 ms | 0 - 57 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
63
+ | EfficientNet-B4 | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 11.795 ms | 0 - 72 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
64
+ | EfficientNet-B4 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 3.441 ms | 0 - 17 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
65
+ | EfficientNet-B4 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 2.275 ms | 0 - 76 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
66
+ | EfficientNet-B4 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 1.928 ms | 0 - 60 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
67
+ | EfficientNet-B4 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 3.885 ms | 121 - 121 MB | NPU | [EfficientNet-B4.dlc](https://huggingface.co/qualcomm/EfficientNet-B4/blob/main/EfficientNet-B4_w8a16.dlc) |
68
 
69
 
70
 
 
122
  ```bash
123
  python -m qai_hub_models.models.efficientnet_b4.export
124
  ```
125
+
 
 
 
 
 
 
 
 
 
 
126
 
127
 
128
  ## 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/EfficientNet-B4.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b361047217af860a0af911629ec00a4069a82cb12210feb87a3e6fb83765a65
3
  size 47410896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9c250b4d558dd2ddd0738fd146342ead98162ba8848647cd52a883c17c60d7d
3
  size 47410896
precompiled/qualcomm-snapdragon-x-elite/EfficientNet-B4.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b332d413435e7b40f7ba8b879d00d47f3230859a44f35d2c10fcea128e158d5
3
- size 37583676
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:759c5898d1589fe688611473fc6adbc7deeeb9fa2b2b4a6e1390e1f3a6bd63f5
3
+ size 37583645
precompiled/qualcomm-snapdragon-x-elite/EfficientNet-B4_w8a16.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db89fef560fc25e13eb5589358eaf9ae7262402517b0ea81e62beb73cfd98e78
3
- size 18590830
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c376ac735f12b012f97cb1e6c6eb93e3cd52aae277427d5d52f4f0aa3b872b79
3
+ size 18590842
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