Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -36,9 +36,9 @@ More details on model performance across various devices, can be found
|
|
36 |
|
37 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
38 |
| ---|---|---|---|---|---|---|---|
|
39 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Binary |
|
40 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Binary |
|
41 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Binary |
|
42 |
|
43 |
|
44 |
## Installation
|
@@ -99,24 +99,24 @@ python -m qai_hub_models.models.stable_diffusion_v1_5_quantized.export
|
|
99 |
```
|
100 |
Profile Job summary of TextEncoder_Quantized
|
101 |
--------------------------------------------------
|
102 |
-
Device:
|
103 |
-
Estimated Inference Time:
|
104 |
-
Estimated Peak Memory Range: 0.
|
105 |
-
Compute Units: NPU (
|
106 |
|
107 |
-
Profile Job summary of
|
108 |
--------------------------------------------------
|
109 |
-
Device:
|
110 |
-
Estimated Inference Time:
|
111 |
-
Estimated Peak Memory Range: 0.
|
112 |
-
Compute Units: NPU (
|
113 |
|
114 |
-
Profile Job summary of
|
115 |
--------------------------------------------------
|
116 |
-
Device:
|
117 |
-
Estimated Inference Time:
|
118 |
-
Estimated Peak Memory Range: 0.
|
119 |
-
Compute Units: NPU (
|
120 |
|
121 |
|
122 |
```
|
|
|
36 |
|
37 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
38 |
| ---|---|---|---|---|---|---|---|
|
39 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Binary | 7.032 ms | 0 - 41 MB | INT8 | NPU | [TextEncoder_Quantized.bin](https://huggingface.co/qualcomm/Stable-Diffusion-v1.5/blob/main/TextEncoder_Quantized.bin)
|
40 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Binary | 232.993 ms | 0 - 38 MB | INT8 | NPU | [VAEDecoder_Quantized.bin](https://huggingface.co/qualcomm/Stable-Diffusion-v1.5/blob/main/VAEDecoder_Quantized.bin)
|
41 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Binary | 127.477 ms | 0 - 52 MB | INT8 | NPU | [UNet_Quantized.bin](https://huggingface.co/qualcomm/Stable-Diffusion-v1.5/blob/main/UNet_Quantized.bin)
|
42 |
|
43 |
|
44 |
## Installation
|
|
|
99 |
```
|
100 |
Profile Job summary of TextEncoder_Quantized
|
101 |
--------------------------------------------------
|
102 |
+
Device: Snapdragon X Elite CRD (11)
|
103 |
+
Estimated Inference Time: 7.64 ms
|
104 |
+
Estimated Peak Memory Range: 0.04-0.04 MB
|
105 |
+
Compute Units: NPU (569) | Total (569)
|
106 |
|
107 |
+
Profile Job summary of VAEDecoder_Quantized
|
108 |
--------------------------------------------------
|
109 |
+
Device: Snapdragon X Elite CRD (11)
|
110 |
+
Estimated Inference Time: 227.24 ms
|
111 |
+
Estimated Peak Memory Range: 0.04-0.04 MB
|
112 |
+
Compute Units: NPU (170) | Total (170)
|
113 |
|
114 |
+
Profile Job summary of UNet_Quantized
|
115 |
--------------------------------------------------
|
116 |
+
Device: Snapdragon X Elite CRD (11)
|
117 |
+
Estimated Inference Time: 129.44 ms
|
118 |
+
Estimated Peak Memory Range: 0.14-0.14 MB
|
119 |
+
Compute Units: NPU (4933) | Total (4933)
|
120 |
|
121 |
|
122 |
```
|