intel/intel-extension-for-transformers

Issues

• Error in import: ModuleNotFoundError: No module named 'neural_compressor.conf'

  #1695 opened 4 months ago by Nicogs43
  8

• 'RuntimeError: "normal_kernel_cpu" not implemented for 'Char'

  #1700 opened 3 months ago by bhaskarachalla
  0

• INSTALL ERRORS PLS HELP!!!

  #1699 opened 3 months ago by c2rx
  0

• After fine-tuning qwen2-1.5B-instruction and quantifying its AWQ, an error occurred while using Intel Extension for Transformers and CPU for inference. But when I used the same method to fine tune and quantify qwen1.5-4B chat before, I could use Intel Extension for Transformers to accelerate CPU inference. 对qwen2-1.5B-instruct微调并且awq量化后，使用intel-extension-for-transformers和CPU进行推理时出错。但我之前使用同样的方式微调和量化的qwen1.5-4B-chat时是可以使用intel-extension-for-transformers加速CPU推理的。

  #1697 opened 4 months ago by Autism-al
  1

• W4A16 LLaMA3 8B quantized model inference failed

  #1694 opened 4 months ago by AustinJiangg
  0

• ModuleNotFoundError: No module named 'neural_compressor.conf'

  #1689 opened 4 months ago by ErvinXie
  7

• intel-extension-for-transformers.ipynb

  #1696 opened 4 months ago by ayttop
  3

• Improve Qlora docs & finetune qwen2-0.5b instruct example

  #1692 opened 4 months ago by bil-ash
  0

• core dumped

  #1690 opened 4 months ago by zwx109473
  1

• Rag example not working

  #1688 opened 4 months ago by anayjain
  1

• Segmentation fault while running rag mode

  #1681 opened 4 months ago by anayjain
  0

• Python3.11: Could not build wheels for cchardet, which is required to install pyproject.toml-based projects

  #1469 opened 9 months ago by bbelky
  3

• is adapt_transformers class adapt any transformer or HF models?

  #1666 opened 5 months ago by sleepingcat4
  1

• How can I use Intel extension for transformers on HPUs?

  #1664 opened 5 months ago by sleepingcat4
  7

• [Feature request] Support for Flashattention 3

  #1665 opened 5 months ago by sleepingcat4
  1

• AutoModelForCausalLM model.generate Wrong response by docker run the same chatglm3-int4 model bin file

  #1680 opened 5 months ago by ahlwjnj
  0

• ImportError: cannot import name 'WeightOnlyQuantizedLinear' from 'intel_extension_for_pytorch.nn.utils._quantize_convert'

  #1630 opened 6 months ago by junruizh2021
  2

• evaluation Parameter Parsing problem

  #1676 opened 5 months ago by 1826133674
  0

• question about configuration

  #1643 opened 6 months ago by menglin0320
  3

• [neural-chat]: deployment backend server failed to start

  #1525 opened 8 months ago by raj-ritu17
  2

• How to config then let the Neural Chat work for chatglm3-6b?

  #1659 opened 6 months ago by ahlwjnj
  0

• Error: Python setup.py egg_info did not run successfully

  #1656 opened 6 months ago by rohitpreddy07
  3

• Compatibility for other platforms, AMD, etc.

  #1649 opened 6 months ago by rain7996
  5

• ITREX: release torch 2.3.x version

  #1644 opened 6 months ago by casper-hansen
  2

• Fails to load saved model : Trying to set a tensor of shape torch.Size([1376, 4096]) in "qweight" (which has shape torch.Size([4096, 1376])), this look incorrect.

  #1407 opened 9 months ago by kranipa
  8

• [Neural_chat] Chat completion is very slow with neuralchat_server

  #1616 opened 6 months ago by noobHappylife
  0

• Support inference with WOQ and LoRA adapter

  #1434 opened 6 months ago by Yuan0320
  3

• ModuleNotFoundError: No module named 'datasets'

  #1461 opened 6 months ago by Aisuko
  2

• talking bot backend for windows-pc is not working, notebook need to be updated

  #1518 opened 6 months ago by raj-ritu17
  3

• Frontend(gradio) string output is not like streaming

  #1524 opened 6 months ago by redhairerINTEL
  4

• ModuleNotFoundError: No module named 'oneccl_bindings_for_pytorch'

  #1574 opened 6 months ago by beam-magnum
  4

• Cannot finish FP4 quantization: `RuntimeError: Qbits: only support Integer WOQ in PACKQ`

  #1577 opened 6 months ago by PhzCode
  6

• Whether FP4 inference is supported

  #1582 opened 6 months ago by PhzCode
  4

• Cannot run llama3 8b instruct: `AssertionError: Fail to convert pytorch model`

  #1522 opened 8 months ago by N3RDIUM
  17

• qloracpu fails, need a conda env list

  #1561 opened 7 months ago by Lix1993
  1

• (detailed) conda install instructions?

  #1550 opened 7 months ago by hpcpony
  2

• unable to start talkingbot frondend

  #1517 opened 8 months ago by raj-ritu17
  5

• rag plugin initialize failed

  #1538 opened 8 months ago by redhairerINTEL
  1

• neuralchat /v1/askdoc/create 404 not found. Failed to call this api on ubuntu system.

  #1533 opened 8 months ago by RongLei-intel
  3

• pip install failure on python3.10-alpine image

  #1379 opened 9 months ago by lrrountr
  2

• ITREX need to do modification for llama3 new prompt format

  #1507 opened 8 months ago by redhairerINTEL
  3

• [Qlora on CPU Error] python finetune_clm.py with Qwen-14B-Chat

  #1484 opened 8 months ago by cailuyu
  4

• NeuralChat TTS plugin unable to initialize due to missing dependency: librosa

  #1490 opened 8 months ago by alexsin368
  1

• Unsupported GPU device: Intel(R) UHD Graphics 770 in version 1.4

  #1463 opened 8 months ago by fakezeta
  2

• RAG example not working..

  #1464 opened 9 months ago by guytamir
  1

• INT4 Inference (CPU) example from README is not working on Windows 11

  #1480 opened 8 months ago by sumeetdas
  3

• No module named 'schema' while fine-tuning neuralchat on Gaudi2

  #1436 opened 9 months ago by alierenak
  2

• Requirements.txt underscores instead of dashes

  #1421 opened 9 months ago by anthony-intel
  7

• failed to create the serving

  #1392 opened 9 months ago by RongLei-intel
  2

• SageMaker does not support Transformers 4.34.1 which is required by ITREX

  #1381 opened 9 months ago by eduand-alvarez
  3