Hugging Face's logo

qualcomm
/
ConvNext-Base

Image Classification
PyTorch
LiteRT
bu_auto
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
e31cdcd
·
verified ·
1 Parent(s): 70bff43

v0.38.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.38.0 for changelog.

Files changed (11) hide show
  1. ConvNext-Base_float.dlc +2 -2
  2. ConvNext-Base_float.onnx.zip +2 -2
  3. ConvNext-Base_w8a16.dlc +2 -2
  4. precompiled/qualcomm-qcs6490-proxy/ConvNext-Base_w8a16.bin → ConvNext-Base_w8a16.onnx.zip +2 -2
  5. README.md +29 -30
  6. precompiled/qualcomm-qcs6490-proxy/tool-versions.yaml +0 -3
  7. precompiled/qualcomm-snapdragon-x-elite/ConvNext-Base_float.bin +0 -3
  8. precompiled/qualcomm-snapdragon-x-elite/ConvNext-Base_float.onnx.zip +0 -3
  9. precompiled/qualcomm-snapdragon-x-elite/ConvNext-Base_w8a16.bin +0 -3
  10. precompiled/qualcomm-snapdragon-x-elite/tool-versions.yaml +0 -3
  11. tool-versions.yaml +3 -2
ConvNext-Base_float.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:668bc917b289d7060b45480be89f833a912ae0d620e2a700ad3c485425e19890
3
- size 354735740
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffac06e692d38cc5d352c954a8cfc3520f59ed840637b66bdb419da5ccb60dba
3
+ size 354735820
ConvNext-Base_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:952b1e201cf68b8d773a1f7e2fda2de64c2aa4f571bc297716561d39f2e0e23a
3
- size 329653180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8903af500719b2453b156b3076b422f39a04fb8835da55d650cb6c9620b42d5
3
+ size 329653288
ConvNext-Base_w8a16.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90869e3085e8d5f8a639277335a856d267e3d6b9a09f4c7450baf97d6696d2d0
3
- size 93047676
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e16171a360971e83f2566d7a810b10765e82529cb4287433d0b60e7a19e719fc
3
+ size 93047700
precompiled/qualcomm-qcs6490-proxy/ConvNext-Base_w8a16.bin → ConvNext-Base_w8a16.onnx.zip RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff4a52dbba96a230e632ad9da6dc705e0b1b304a84c3602023c377c75aef765e
3
- size 118919168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d0c399930854b6e8d9ca30a27d1bdc93a1bc2e7ff70496bf9b2a397a71d32c4
3
+ size 303871056
README.md CHANGED
@@ -36,35 +36,34 @@ 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
- | ConvNext-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 41.59 ms | 0 - 231 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 | 42.288 ms | 1 - 236 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 | 18.272 ms | 0 - 247 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 | 20.554 ms | 1 - 248 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 | 7.377 ms | 0 - 23 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 | 8.121 ms | 1 - 24 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
45
- | ConvNext-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 7.438 ms | 0 - 24 MB | NPU | [ConvNext-Base.onnx.zip](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx.zip) |
46
- | ConvNext-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 11.363 ms | 0 - 231 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
47
- | ConvNext-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 11.975 ms | 1 - 236 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 | TFLITE | 7.313 ms | 0 - 25 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
49
- | ConvNext-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 8.153 ms | 1 - 24 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
50
- | ConvNext-Base | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 7.449 ms | 0 - 23 MB | NPU | [ConvNext-Base.onnx.zip](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx.zip) |
51
- | ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.563 ms | 0 - 244 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
52
- | ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 6.009 ms | 1 - 244 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
53
- | ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.483 ms | 1 - 242 MB | NPU | [ConvNext-Base.onnx.zip](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx.zip) |
54
- | ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 4.809 ms | 0 - 235 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
55
- | ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 5.34 ms | 1 - 239 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
56
- | ConvNext-Base | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 5.044 ms | 0 - 234 MB | NPU | [ConvNext-Base.onnx.zip](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx.zip) |
57
- | ConvNext-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 8.501 ms | 1229 - 1229 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
58
- | ConvNext-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 7.461 ms | 176 - 176 MB | NPU | [ConvNext-Base.onnx.zip](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx.zip) |
59
- | ConvNext-Base | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 14.365 ms | 0 - 128 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
60
- | ConvNext-Base | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 9.039 ms | 0 - 139 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
61
- | ConvNext-Base | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 5.843 ms | 0 - 32 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
62
- | ConvNext-Base | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 6.108 ms | 0 - 127 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
63
- | ConvNext-Base | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 33.238 ms | 0 - 219 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 | QNN_DLC | 5.862 ms | 0 - 32 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 | QNN_DLC | 4.139 ms | 0 - 140 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
66
- | ConvNext-Base | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 3.752 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 X Elite CRD | Snapdragon® X Elite | QNN_DLC | 6.232 ms | 454 - 454 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
68
 
69
 
70
 
@@ -146,7 +145,7 @@ from qai_hub_models.models.convnext_base import Model
146
  torch_model = Model.from_pretrained()
147
 
148
  # Device
149
- device = hub.Device("Samsung Galaxy S24")
150
 
151
  # Trace model
152
  input_shape = torch_model.get_input_spec()
 
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 | 41.646 ms | 0 - 232 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 | 42.265 ms | 1 - 235 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 | 18.229 ms | 0 - 246 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 | 20.611 ms | 1 - 248 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 | 7.399 ms | 0 - 24 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 | 8.14 ms | 0 - 24 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
45
+ | ConvNext-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 7.4 ms | 1 - 23 MB | NPU | [ConvNext-Base.onnx.zip](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx.zip) |
46
+ | ConvNext-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 11.388 ms | 0 - 232 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
47
+ | ConvNext-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 11.964 ms | 1 - 237 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
48
+ | ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.559 ms | 0 - 247 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
49
+ | ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 5.953 ms | 1 - 246 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
50
+ | ConvNext-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.452 ms | 0 - 250 MB | NPU | [ConvNext-Base.onnx.zip](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx.zip) |
51
+ | ConvNext-Base | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 4.156 ms | 0 - 234 MB | NPU | [ConvNext-Base.tflite](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.tflite) |
52
+ | ConvNext-Base | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 4.584 ms | 0 - 239 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
53
+ | ConvNext-Base | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 4.244 ms | 0 - 237 MB | NPU | [ConvNext-Base.onnx.zip](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx.zip) |
54
+ | ConvNext-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 8.519 ms | 1268 - 1268 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.dlc) |
55
+ | ConvNext-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 7.471 ms | 176 - 176 MB | NPU | [ConvNext-Base.onnx.zip](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base.onnx.zip) |
56
+ | ConvNext-Base | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 14.372 ms | 0 - 128 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
57
+ | ConvNext-Base | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 9.115 ms | 0 - 139 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
58
+ | ConvNext-Base | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 5.849 ms | 0 - 36 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
59
+ | ConvNext-Base | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 6.104 ms | 0 - 127 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
60
+ | ConvNext-Base | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 33.51 ms | 0 - 219 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) | ONNX | 624.104 ms | 38 - 57 MB | CPU | [ConvNext-Base.onnx.zip](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx.zip) |
62
+ | ConvNext-Base | w8a16 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 650.719 ms | 36 - 136 MB | CPU | [ConvNext-Base.onnx.zip](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx.zip) |
63
+ | ConvNext-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 4.172 ms | 0 - 138 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
64
+ | ConvNext-Base | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 3.237 ms | 0 - 130 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
65
+ | ConvNext-Base | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 162.984 ms | 645 - 1277 MB | NPU | [ConvNext-Base.onnx.zip](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.onnx.zip) |
66
+ | ConvNext-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 6.179 ms | 479 - 479 MB | NPU | [ConvNext-Base.dlc](https://huggingface.co/qualcomm/ConvNext-Base/blob/main/ConvNext-Base_w8a16.dlc) |
 
67
 
68
 
69
 
 
145
  torch_model = Model.from_pretrained()
146
 
147
  # Device
148
+ device = hub.Device("Samsung Galaxy S25")
149
 
150
  # Trace model
151
  input_shape = torch_model.get_input_spec()
precompiled/qualcomm-qcs6490-proxy/tool-versions.yaml DELETED
@@ -1,3 +0,0 @@
1
- tool_versions:
2
- qnn_context_binary:
3
- qairt: 2.37.0.250724175447_124859
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/ConvNext-Base_float.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:02bd7d31ffe679b9c4545c555649fbf119d2d485412ed63d1d04e7199f07487b
3
- size 184098816
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/ConvNext-Base_float.onnx.zip DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9cf57e398f586d3de3a4a166a7fea51dc712d65c9800439b6e46b9d214050b2
3
- size 166005350
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/ConvNext-Base_w8a16.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7144498757b3a3177baa5731f82b4c9529807002ff3cd401efbd7eb6d7536427
3
- size 95387648
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/tool-versions.yaml DELETED
@@ -1,3 +0,0 @@
1
- tool_versions:
2
- qnn_context_binary:
3
- qairt: 2.37.0.250724175447_124859
 
 
 
 
tool-versions.yaml CHANGED
@@ -1,3 +1,4 @@
1
  tool_versions:
2
- qnn_dlc:
3
- qairt: 2.37.0.250724175447_124859
 
 
1
  tool_versions:
2
+ onnx:
3
+ qairt: 2.37.1.250807093845_124904
4
+ onnx_runtime: 1.22.2