quic/ai-hub-models

Issues

• Android App to run Llama-v2-7B-Chat Quantized INT4 on my Android Device

  #62 opened 6 months ago by taeyeonlee
  13

• [BUG] ViT export stopped working correctly

  #73 opened 2 months ago by Lavreniuk
  2

• [Feature Request] Provides file input for local testing

  #71 opened 2 months ago by shifeiwen
  2

• [Feature Request] Locally run Stable Diffusion on X Elite devices

  #55 opened 6 months ago by Aloereed
  2

• Using NPU in ImageClassification demo app

  #51 opened 2 months ago by ciaranbor
  3

• Image_Classification apk is crashed after device runtime is selected

  #36 opened 2 months ago by axcpy08
  2

• [BUG] Model with element-wise select / torch.where() fails to finalize

  #27 opened 2 months ago by mako443
  2

• Execute quantized model on TFLite with QCS6490

  #26 opened 2 months ago by mbenencase
  3

• dynamic dimension shape input

  #52 opened 2 months ago by zhuzhu18
  1

• [MODEL REQUEST] Phi-3

  #65 opened 6 months ago by EwoutH
  2

• [BUG] Can hub.submit_inference_job API use online models?

  #77 opened 4 months ago by songh11
  2

• [MODEL REQUEST] Florence-2

  #57 opened 6 months ago by EwoutH
  3

• NO of Inference Set to 20 or 30

  #75 opened 5 months ago by Vinaysukhesh98
  2

• Incorrect Comment

  #47 opened 5 months ago by BHilldore
  2

• [Feature Request] How to run Whisper on the 8550 LE system

  #53 opened 6 months ago by 32zhuyt
  2

• error occured when I run llama_v2_7b_chat_quantized

  #76 opened 5 months ago by yolanda1224git
  4

• pacakage error

  #48 opened 5 months ago by Vinaysukhesh98
  4

• [BUG] SemanticSegmentation File missing, unable to execute

  #74 opened 5 months ago by ZhangY427
  3

• [Feature Request] export other model document

  #72 opened 5 months ago by shifeiwen
  1

• سکس

  #70 opened 5 months ago by Alijmali1352
  1

• [Llama] how to run QNN Context Binary for Llama model on my Galaxy S24 mobile ?

  #67 opened 5 months ago by taeyeonlee
  11

• سکس

  #69 opened 5 months ago by 5uhfut
  0

• [BUG] fail to convert QNN Source to QNN Model Library (qnn-model-lib-generator) for Llama v2_7b_chat_quantized

  #64 opened 5 months ago by taeyeonlee
  3

• Failure Reason Must use --truncate_64bit_io when input tensors have type int64.

  #68 opened 6 months ago by AndreaChiChengdu
  0

• [BUG] Empty Error of Llama-v2-7B-Chat Repo on Huggingface

  #66 opened 6 months ago by MaTwickenham
  1

• [Feature Request] Change the super resolution algorithm solution

  #63 opened 6 months ago by vongocminh778
  1

• [MODEL REQUEST] Gemma 2 (9B and 27B)

  #60 opened 6 months ago by EwoutH
  0

• [MODEL REQUEST] Codestral-22B

  #59 opened 6 months ago by EwoutH
  1

• [MODEL REQUEST] Kosmos-2.5

  #58 opened 6 months ago by EwoutH
  1

• Why Pad before Conv2D in yolov8_det_quantized tflite model

  #54 opened 6 months ago by richjjj
  1

• [Feature Request] OpenPose model has no option to use .bin file as target runtime.

  #56 opened 6 months ago by ukc-work
  1

• [BUG] 3x Conv-3 Layers runs out of memory on Hub

  #22 opened 6 months ago by mestrona-3
  2

• import com.qualcomm2.QnnDelegate fail

  #50 opened 6 months ago by tumuyan
  1

• [Feature Request] Linux on ARM

  #46 opened 6 months ago by phodina
  5

• Label.txt file for yolov8_det.tflite model

  #43 opened 7 months ago by MuhammadShifa
  1

• apps/android Building Android APP failed

  #30 opened 9 months ago by ZhangWeiOneTwo
  6

• [Feature Request] ControlNet app sample

  #44 opened 7 months ago by Mengmengbai
  2

• [BUG] ModuleNotFoundError: No module named 'ffnet_datasets'

  #45 opened 7 months ago by LawrenceMeng
  1

• How to quantize LLM to INT4?

  #29 opened 7 months ago by YixinSong-e
  5

• [BUG] Improvements for apps/Android/ImageClassification/build_apk.py

  #38 opened 7 months ago by fangxingSR
  2

• [Feature Request] Additional Profiling Statistics

  #42 opened 8 months ago by jasonw247
  1

• [BUG] Controlnet models are providing noisy image outputs

  #37 opened 8 months ago by kristoftunner
  1

• [Feature Request] 16:9 ratio input image for controlnet

  #25 opened 9 months ago by kristoftunner
  4

• [BUG] openAI-Clip demo failed on cuda machine

  #21 opened 8 months ago by mestrona-3
  1

• No such file or directory: '/opt/qcom/aistack/qairt/2.21.0.240401/lib/android/qtld-release.aar'

  #33 opened 9 months ago by fangxingSR
  10

• [BUG] Model fails in ONNX export with relu6 op not supported

  #23 opened 9 months ago by mestrona-3
  0

• Add RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose

  #31 opened 9 months ago by GLOMQuyet
  1

• Performance issue

  #28 opened 9 months ago by YixinSong-e
  1

• Benchmarks for QCS610 and QCS6490

  #20 opened 9 months ago by mbenencase
  2

• [Feature Request] Whisper Prompting feature

  #24 opened 9 months ago by cfasana
  2