intel/intel-npu-acceleration-library

Issues

• NPU utilization for maths problems

  #51 opened 4 months ago by KhDenys
  8

• Dose linear support input_tensor with dtype int8?

  #57 opened 3 months ago by Septend-fun
  4

• NPU computation is not fully occupied while running LLM model

  #55 opened 4 months ago by nigue3025
  3

• Error when running Phi-3-mini-128k int4 on Windows

  #77 opened 3 months ago by Ce-daros
  2

• Question about 'scaled_dot_product_attention' function

  #75 opened 3 months ago by xduzhangjiayu
  3

• matmul.py giving error below (ubuntu 22.04 on intel + NPU)

  #64 opened 3 months ago by rahulish75
  2

• No module named 'transformers_modules'

  #69 opened 3 months ago by goxia
  3

• Run Phi-3 on the Intel NPU there's issue

  #67 opened 3 months ago by goxia
  5

• cannot compile the depthwise conv when it is included in other models

  #52 opened 3 months ago by wcshds
  2

• NPU compiled Llama3 (int4) model not working if prompt size is large

  #40 opened 4 months ago by sujikarNStarx
  3

• Problem with 'generate_with_static_shape' function

  #59 opened 3 months ago by xduzhangjiayu
  4

• Failed to run Phi-3-mini-4k-instruct (torch.int8) on Windows #45

  #48 opened 3 months ago by aoke79
  9

• RuntimeError occurs when run quantized int8 Llama-2-7b-hf

  #56 opened 3 months ago by weberwcwei
  5

• Compile question about using c++ API.

  #53 opened 4 months ago by Septend-fun
  2

• cannot compile `nn.Sequential` into float32

  #49 opened 4 months ago by wcshds
  4

• Failed to run Phi-3-mini-4k-instruct (int4) on Windows

  #45 opened 4 months ago by xyang2013
  9

• Profiling and Allocation Control for Partially Offloaded Models

  #29 opened 4 months ago by BICHENG
  3

• Phi-3-mini-4k-instruct (INT4) model compile error

  #44 opened 4 months ago by xyang2013
  1

• Does this library work with wsl2?

  #13 opened 6 months ago by tackgeun
  6

• What Intel CPU can we run this library ?

  #5 opened 4 months ago by jawaechan
  1

• [Bug] when cache read on Phi-3 example, error occur.

  #42 opened 4 months ago by invent00
  3

• Persistent Compiled Model for Intel NPU Acceleration Library

  #26 opened 4 months ago by BICHENG
  2

• [Bug] int8 quantization not working except tiny llama

  #33 opened 4 months ago by invent00
  5

• [Question]NPU is slower than CPU when computing some types of matmul.

  #41 opened 4 months ago by Septend-fun
  4

• "OSError: [WinError -529697949] Windows Error 0xe06d7363 “ - While running llama3 on NPU

  #37 opened 4 months ago by sujikarNStarx
  2

• Get confused of why Llama example can run on win10

  #34 opened 4 months ago by nigue3025
  4

• profile_llm.py fails with default arguments

  #23 opened 4 months ago by rradjabi
  6

• Installing package from source fails

  #24 opened 4 months ago by rradjabi
  1

• microsoft/phi-2 model outputs nonsense on NPU

  #27 opened 4 months ago by flomader
  6

• pip install intel-npu-acceleration-library ERROR

  #30 opened 4 months ago by qwebug
  2

• DirectML vs This Package

  #25 opened 5 months ago by DavidMartinezGonzalez
  0

• ERROR: Failed building wheel for intel-npu-acceleration-library

  #22 opened 5 months ago by henry8248
  2

• [Bug] Tiny Llama sample not works properly

  #17 opened 5 months ago by invent00
  4

• support whisper model.

  #10 opened 5 months ago by mushuanli
  1

• Need help with OSError: [WinError -529697949] Windows Error 0xe06d7363

  #14 opened 5 months ago by hhirche
  5

• Why is the matrix multiplication slower after I installed the NPU driver?

  #16 opened 6 months ago by BingoZha
  9

• CPU and NPU Hybrid Training Model

  #12 opened 6 months ago by MansonHua
  1

• Can you clarify if the NPU is the same component as the GNA and are both supported?

  #15 opened 6 months ago by steevithak
  1

• Add support for BitNet b1.58 quantization

  #3 opened 7 months ago by vegax87
  4

• Request to provide a RAG example?

  #7 opened 6 months ago by ChenYuYeh
  12

• AttributeError: property 'pad_token_id' of 'ChatGLMTokenizer' object has no setter

  #9 opened 7 months ago by andyluo7
  2

• [OSError][WinError-529697949][Intel Meteorlake] Error when try to run example matmul.py

  #8 opened 7 months ago by kurtqiao
  3

• Future Plan about this library.

  #6 opened 7 months ago by BismarckDD
  0

• What Intel CPU can we run this library ?

  #4 opened 7 months ago by jawaechan
  0

• Keras support

  #2 opened 7 months ago by SamuelMarks
  0