quic/ai-hub-models

Issues

• Please consider publishing to PyPI for Python-3.11 and 3.12

  #108 opened a month ago by atiorh
  1

• [BUG] IOT BYOM Issue: <insert issue here>

  #128 opened a month ago by mbenencase
  1

• [Feature Request] Add the use of https://pypi.org/project/torch-npu/ to enable the NPU of x1e-78-100

  #127 opened a month ago by BrickDesignerNL
  2

• [Feature Request] New feature request

  #125 opened a month ago by 1826133674
  1

• [Question] What's the groupsize of w4a16 + w8a16

  #112 opened 2 months ago by xiguadong
  1

• [BUG] Fail to run llama v2 7B quantized on Galaxy S24 Ultra using GENIE C API

  #102 opened 3 months ago by taeyeonlee
  4

• [BUG] Error exporting OpenAI-Clip

  #110 opened a month ago by rachillesf
  1

• [question] Can I deploy LLM on SA8295 with Hexagon v68?

  #124 opened a month ago by ecccccsgo
  1

• [BUG] Ollama not using GPU and not using NPU

  #126 opened a month ago by BrickDesignerNL
  2

• [BUG] Windows install Whisper not working

  #123 opened a month ago by BrickDesignerNL
  7

• qai-hub SDV2_1 demo running question

  #120 opened 2 months ago by 1826133674
  2

• [BUG] Wrong Device/CPU detection & Using deprecated function & Key needed for demo & Should run local, but uploads model & Very slow Qualcomm cloud

  #122 opened 2 months ago by BrickDesignerNL
  8

• [MODEL REQUEST] Whisper-large-v3

  #115 opened 2 months ago by BrickDesignerNL
  1

• [MODEL REQUEST] Bark - text to singing & sound effects - from suno.ai / suno.com

  #116 opened 2 months ago by BrickDesignerNL
  1

• [MODEL REQUEST] Music generating & Voice cloning models

  #117 opened 2 months ago by BrickDesignerNL
  1

• [MODEL REQUEST] Stable-Diffusion-v3.5 & safetensor files

  #118 opened 2 months ago by BrickDesignerNL
  1

• [MODEL REQUEST] Fundamentals of Music Processing (FMP)

  #121 opened 2 months ago by BrickDesignerNL
  0

• [MODEL FORMAT REQUEST] Support safetensors

  #119 opened 2 months ago by BrickDesignerNL
  0

• [BUG] File bug report : After logging in again, user is presented with login screen.

  #111 opened 2 months ago by quic-rneti
  1

• [BUG] Repo incompatible with Python 3.12.7 (ARM64) & 3.11.8 (ARM64). Lower versions of Python for Windows aren't available for ARM64. - Snapdragon X Elite has no native working version.

  #113 opened 2 months ago by BrickDesignerNL
  6

• [BUG] YoLo (and other models) DEMO not working - dataset folder is locally available but reference is not correct

  #114 opened 2 months ago by BrickDesignerNL
  1

• ModuleNotFoundError: No module named 'libPyIrGraph'

  #97 opened 3 months ago by Harsha0056
  13

• [Feature Request] Whisper Small.En Quantized

  #81 opened 5 months ago by Carl-2008
  2

• qti.tvm.error.OpNotImplemented: The following operators are not supported in frontend TFLite: 'GELU'

  #104 opened 2 months ago by chenxiao521
  1

• [BUG] genie-t2t-run Fails to run llama v2 7B quantized on Galaxy S23 Ultra

  #101 opened 3 months ago by taeyeonlee
  3

• [BUG] Error running LLaMA2_7B_Chat_Quantized on 8gen3 device.

  #109 opened 2 months ago by LLIKKE
  0

• [BUG] File bug report I'm having a problem installing the gen_ondevice_llama operation on my phone deploying llama to run on the final phone

  #107 opened 2 months ago by LLIKKE
  2

• [Feature Request] New feature request

  #106 opened 2 months ago by holylong
  2

• In QCS8550 development board, the inference of llama-v2-7b-chat using NPU failed."

  #105 opened 2 months ago by holylong
  3

• [BUG] IOT BYOM Issue: Compiling PyTorch model to a QNN Context Binary on AiHub fails

  #95 opened 3 months ago by Midi12
  7

• [Feature Request] whisper android app and native app

  #99 opened 3 months ago by leemeng0x61
  1

• Running Model Locally with Custom Prompts

  #96 opened 3 months ago by xuandy05
  1

• [BUG] Mobile BYOM Issue: How to generate .tflite models form export?

  #94 opened 3 months ago by XinyuGroceryStore
  3

• What is the limitation of Hexagon V75 that the Llama v2 7B Quantized model should be split into 8 Bin files ?

  #100 opened 3 months ago by taeyeonlee
  1

• No Python on Windows ARM available for < 3.11

  #89 opened 3 months ago by nsteblay
  6

• [Genie] fails to generate genie-compatible QNN binaries

  #98 opened 3 months ago by taeyeonlee
  4

• QCT Genie SDK (genie-t2t-run) : Llama v2 7B performance

  #80 opened 3 months ago by taeyeonlee
  7

• QCT Genie SDK (genie-t2t-run) fails to run on QNN HTP backend

  #82 opened 3 months ago by taeyeonlee
  4

• [BUG] The generated text is strange from 8 QNN Context Bins which are generated in AI Hub.

  #87 opened 3 months ago by taeyeonlee
  4

• [BUG] fails to create context from binary for the 4 QNN Context Bin files (llama_v2_7b_chat_quantized_TokenGenerator_x_Quantized.bin)

  #85 opened 3 months ago by taeyeonlee
  3

• Does not support XR2 GEN2 chip?

  #92 opened 4 months ago by brisyramshere
  1

• [BUG] Mobile BYOM Issue: <insert issue here> OnePlus 9 Pro modelo LE2121

  #93 opened 4 months ago by Alexanbezerra
  2

• Has the AiHub's Whisper model been retrained?

  #90 opened 4 months ago by zzy981019
  2

• [BUG] Mobile BYOM Issue: <insert issue here>

  #91 opened 4 months ago by weekendcheng
  1

• [Question] Does the DLC engine only have one output?

  #88 opened 4 months ago by Carl-2008
  2

• [Question] Where did your tflite model come from？

  #86 opened 4 months ago by Ss-shuang123
  1

• Operate with NPU

  #83 opened 5 months ago by a4073631
  1

• Genie C API : Sample android app

  #79 opened 5 months ago by taeyeonlee
  1

• error occured when run llama_v2_7b_chat_quantized_PromptProcessor_3_Quantized

  #84 opened 5 months ago by yolanda1224git
  1

• Error uploading to QDC: status code=500

  #78 opened 5 months ago by yolanda1224git
  0