v0.62.0

See https://github.com/qualcomm/ai-hub-models/releases/v0.62.0 for changelog.

README.md

@@ -17,7 +17,7 @@ pipeline_tag: text-generation
 Qwen3-VL is a vision-language model from Alibaba Cloud capable of understanding both text and images for multimodal reasoning tasks such as visual question answering and image captioning.
 
 This is based on the implementation of Qwen3-VL-2B-Instruct found [here](https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct).
-This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/qwen3_vl_2b_instruct) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
+This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.62.0/src/qai_hub_models/models/qwen3_vl_2b_instruct) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
 
 Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
 
@@ -41,14 +41,14 @@ For more device-specific assets and performance metrics, visit **[Qwen3-VL-2B-In
 
 ### Option 2: Export with Custom Configurations
 
-Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/qwen3_vl_2b_instruct) Python library to compile and export the model with your own:
+Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.62.0/src/qai_hub_models/models/qwen3_vl_2b_instruct) Python library to compile and export the model with your own:
 - Custom weights (e.g., fine-tuned checkpoints)
 - Custom input shapes
 - Target device and runtime configurations
 
 This option is ideal if you need to customize the model beyond the default configuration provided here.
 
-See our repository for [Qwen3-VL-2B-Instruct on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/qwen3_vl_2b_instruct) for usage instructions.
+See our repository for [Qwen3-VL-2B-Instruct on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.62.0/src/qai_hub_models/models/qwen3_vl_2b_instruct) for usage instructions.
 
 ## Model Details
 
@@ -63,33 +63,36 @@ See our repository for [Qwen3-VL-2B-Instruct on GitHub](https://github.com/qualc
 ## Performance Summary
 | Model | Runtime | Precision | Chipset | Context Length | Response Rate (tokens per second) | Time To First Token (range, seconds)
 |---|---|---|---|---|---|---
-| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® 8 Elite Mobile | 512 | 41.543766 | 0.46449075 - 1.857963
-| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® 8 Elite Mobile | 512 | 42.711314 | 0.46647375 - 1.865895
-| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® 8 Elite Mobile | 512 | 34.032126 | 0.11172275000000001 - 0.44689100000000004
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® 8 Elite Mobile | 512 | 47.430332 | 0.3327866666666666 - 1.3311466666666665
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® 8 Elite Mobile | 512 | 32.88392 | 0.217985 - 0.87194
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® 8 Elite Mobile | 512 | 29.964567 | 0.069595 - 0.27838
 | Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® X2 Elite | 512 | 62.900994 | 0.1141745 - 0.456698
 | Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® X2 Elite | 512 | 64.127228 | 0.112751 - 0.451004
 | Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® X2 Elite | 512 | 23.365032 | 0.07905475 - 0.316219
 | Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® X2 Elite | 4096 | 30.033638 | 0.23735575 - 7.595384
 | Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® X2 Elite | 4096 | 26.100461 | 0.23745440625 - 7.598541
 | Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® X2 Elite | 4096 | 20.902282 | 0.108134125 - 3.460292
-| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® X Elite | 512 | 21.177916 | 0.1795745 - 0.718298
-| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® X Elite | 512 | 20.103331 | 0.18485975 - 0.739439
-| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® X Elite | 512 | 24.308468 | 0.16061474999999997 - 0.6424589999999999
-| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® X Elite | 4096 | 15.733537 | 0.43978756249999995 - 14.073201999999998
-| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® X Elite | 4096 | 15.966534 | 0.46862746875 - 14.996079
-| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® X Elite | 4096 | 11.584063 | 0.24593868749999998 - 7.870037999999999
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® X Elite | 512 | 32.439446 | 0.2918443333333333 - 1.1673773333333333
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® X Elite | 512 | 32.311222 | 0.21815833333333334 - 0.8726333333333334
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® X Elite | 512 | 26.440463 | 0.13286633333333334 - 0.5314653333333333
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® X Elite | 4096 | 24.39174 | 0.4940118387096774 - 15.808378838709677
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® X Elite | 4096 | 15.302921 | 0.49661099999999997 - 15.891551999999999
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Snapdragon® X Elite | 4096 | 11.823476 | 0.16016632258064517 - 5.1253223225806455
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ IQ-8275 | 512 | 10.77804 | 1.622459 - 6.489836
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ IQ-8275 | 512 | 4.418073 | 2.3404373333333335 - 9.361749333333334
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ IQ-8275 | 512 | 3.523704 | 0.2616836666666667 - 1.0467346666666668
 | Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ IQ-9075 | 512 | 1.882364 | 1.1826937499999999 - 4.7307749999999995
 | Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ IQ-9075 | 512 | 1.878065 | 1.18503875 - 4.740155
 | Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ IQ-9075 | 512 | 19.881743 | 0.18957975 - 0.758319
-| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ IQ-X7181 | 512 | 21.177916 | 0.1795745 - 0.718298
-| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ IQ-X7181 | 512 | 20.103331 | 0.18485975 - 0.739439
-| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ IQ-X7181 | 512 | 24.308468 | 0.16061474999999997 - 0.6424589999999999
-| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ Q-8750 | 512 | 41.543766 | 0.46449075 - 1.857963
-| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ Q-8750 | 512 | 42.711314 | 0.46647375 - 1.865895
-| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ Q-8750 | 512 | 34.032126 | 0.11172275000000001 - 0.44689100000000004
-| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ IQ-X7181 | 4096 | 15.733537 | 0.43978756249999995 - 14.073201999999998
-| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ IQ-X7181 | 4096 | 15.966534 | 0.46862746875 - 14.996079
-| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ IQ-X7181 | 4096 | 11.584063 | 0.24593868749999998 - 7.870037999999999
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ IQ-X7181 | 512 | 32.439446 | 0.2918443333333333 - 1.1673773333333333
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ IQ-X7181 | 512 | 32.311222 | 0.21815833333333334 - 0.8726333333333334
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ IQ-X7181 | 512 | 26.440463 | 0.13286633333333334 - 0.5314653333333333
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ Q-8750 | 512 | 47.430332 | 0.3327866666666666 - 1.3311466666666665
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ Q-8750 | 512 | 32.88392 | 0.217985 - 0.87194
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ Q-8750 | 512 | 29.964567 | 0.069595 - 0.27838
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ IQ-X7181 | 4096 | 24.39174 | 0.4940118387096774 - 15.808378838709677
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ IQ-X7181 | 4096 | 15.302921 | 0.49661099999999997 - 15.891551999999999
+| Qwen3-VL-2B-Instruct | GENIEX_LLAMACPP | q4_0 | Qualcomm® Dragonwing™ IQ-X7181 | 4096 | 11.823476 | 0.16016632258064517 - 5.1253223225806455
 
 ## License
 * The license for the original implementation of Qwen3-VL-2B-Instruct can be found

release_assets.json

@@ -1,5 +1,5 @@
 {
-    "version": "0.61.0",
+    "version": "0.62.0",
     "precisions": {
         "q4_0": {
             "universal_assets": {