intel/intel-extension-for-transformers issues and pull requests

#1700 - 'RuntimeError: "normal_kernel_cpu" not implemented for 'Char'

Issue - State: open - Opened by bhaskarachalla about 1 month ago

#1699 - INSTALL ERRORS PLS HELP!!!

Issue - State: open - Opened by c2rx about 2 months ago

#1698 - Bump langchain from 0.1.11 to 0.2.10 in /intel_extension_for_transformers/neural_chat/tests

Pull Request - State: open - Opened by dependabot[bot] about 2 months ago - 1 comment
Labels: dependencies, python

#1697 - 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。

Issue - State: open - Opened by Autism-al 2 months ago - 1 comment

#1696 - intel-extension-for-transformers.ipynb

Issue - State: open - Opened by ayttop 3 months ago - 3 comments

#1695 - Error in import: ModuleNotFoundError: No module named 'neural_compressor.conf'

Issue - State: open - Opened by Nicogs43 3 months ago - 7 comments

#1694 - W4A16 LLaMA3 8B quantized model inference failed

Issue - State: closed - Opened by AustinJiangg 3 months ago

#1693 - Add readme for inc 3.0 xpu device usage

Pull Request - State: open - Opened by changwangss 3 months ago - 1 comment

#1692 - Improve Qlora docs & finetune qwen2-0.5b instruct example

Issue - State: open - Opened by bil-ash 3 months ago

#1691 - Update utils.py

Pull Request - State: open - Opened by changwangss 3 months ago - 1 comment

#1690 - core dumped

Issue - State: open - Opened by zwx109473 3 months ago - 1 comment

#1689 - ModuleNotFoundError: No module named 'neural_compressor.conf'

Issue - State: closed - Opened by ErvinXie 3 months ago - 7 comments

#1688 - Rag example not working

Issue - State: open - Opened by anayjain 3 months ago - 1 comment

#1687 - fix search issue of online doc

Pull Request - State: closed - Opened by NeoZhangJianyu 3 months ago - 1 comment

#1686 - Adapt `INCWeightOnlyLinear`

Pull Request - State: closed - Opened by Kaihui-intel 3 months ago - 1 comment

#1685 - Update LLM recipes to align INC 3.0

Pull Request - State: closed - Opened by XuehaoSun 3 months ago - 1 comment

#1684 - Fix intel tbb

Pull Request - State: closed - Opened by XuehaoSun 3 months ago - 1 comment

#1683 - Add `use_mse_search` to GPTQ Config

Pull Request - State: closed - Opened by Kaihui-intel 3 months ago - 1 comment

#1682 - fix int8 skip module config

Pull Request - State: closed - Opened by changwangss 3 months ago - 3 comments

#1681 - Segmentation fault while running rag mode

Issue - State: closed - Opened by anayjain 3 months ago

#1680 - AutoModelForCausalLM model.generate Wrong response by docker run the same chatglm3-int4 model bin file

Issue - State: open - Opened by ahlwjnj 4 months ago

#1679 - Bump torch from 1.13.1 to 2.2.0 in /workflows/compression_aware_training

Pull Request - State: open - Opened by dependabot[bot] 4 months ago - 1 comment
Labels: dependencies, python

#1678 - Bump langchain-community from 0.0.27 to 0.2.9 in /intel_extension_for_transformers/neural_chat/pipeline/plugins/retrieval

Pull Request - State: open - Opened by dependabot[bot] 4 months ago - 1 comment
Labels: dependencies, python

#1677 - Update publication.md

Pull Request - State: closed - Opened by kevinintel 4 months ago - 1 comment

#1676 - evaluation Parameter Parsing problem

Issue - State: open - Opened by 1826133674 4 months ago

#1675 - Fix args.tasks type check issue

Pull Request - State: closed - Opened by duanshengliu 4 months ago - 2 comments

#1674 - test ci

Pull Request - State: closed - Opened by changwangss 4 months ago - 1 comment

#1673 - For test

Pull Request - State: closed - Opened by XuehaoSun 4 months ago - 1 comment

#1672 - qbits deprecate clip postfix

Pull Request - State: open - Opened by zhewang1-intc 4 months ago

#1671 - Adapt quant lm head

Pull Request - State: closed - Opened by changwangss 4 months ago - 3 comments

#1670 - Support lmhead int4

Pull Request - State: open - Opened by a32543254 4 months ago

#1669 - Adapt INC autoround changes

Pull Request - State: closed - Opened by changwangss 4 months ago - 4 comments

#1668 - Fix CI inc3.x install

Pull Request - State: closed - Opened by XuehaoSun 4 months ago - 1 comment

#1667 - Bump setuptools from 69.5.1 to 70.0.0

Pull Request - State: closed - Opened by dependabot[bot] 4 months ago - 2 comments
Labels: dependencies, python

#1666 - is adapt_transformers class adapt any transformer or HF models?

Issue - State: closed - Opened by sleepingcat4 4 months ago - 1 comment
Labels: habana

#1665 - [Feature request] Support for Flashattention 3

Issue - State: closed - Opened by sleepingcat4 4 months ago - 1 comment

#1664 - How can I use Intel extension for transformers on HPUs?

Issue - State: closed - Opened by sleepingcat4 4 months ago - 7 comments

#1663 - A beginner friendly quantize and text embeddings tutorial for XPUs

Pull Request - State: open - Opened by sleepingcat4 4 months ago - 3 comments

#1662 - improve SQ/WOQ examples

Pull Request - State: closed - Opened by changwangss 4 months ago - 1 comment

#1661 - Bump protobuf from 3.20 to 3.20.2 in /intel_extension_for_transformers/neural_chat/pipeline/plugins/retrieval

Pull Request - State: closed - Opened by dependabot[bot] 4 months ago - 1 comment
Labels: dependencies, python

#1660 - Update publication.md

Pull Request - State: closed - Opened by kevinintel 4 months ago - 1 comment

#1659 - How to config then let the Neural Chat work for chatglm3-6b?

Issue - State: open - Opened by ahlwjnj 4 months ago

#1658 - update lm-eval to 0.4.3

Pull Request - State: closed - Opened by changwangss 4 months ago - 2 comments

#1657 - Apply regreSSHion mitigation

Pull Request - State: closed - Opened by tylertitsworth 4 months ago

#1656 - Error: Python setup.py egg_info did not run successfully

Issue - State: closed - Opened by rohitpreddy07 4 months ago - 3 comments

#1655 - Enable modelscope for itrex

Pull Request - State: open - Opened by intellinjun 4 months ago - 2 comments

#1654 - Fix optimum-intel version for INC v3.0

Pull Request - State: closed - Opened by changwangss 4 months ago - 1 comment

#1653 - qbits support f4 weight repack

Pull Request - State: closed - Opened by zhewang1-intc 4 months ago - 2 comments

#1652 - for test

Pull Request - State: closed - Opened by XuehaoSun 4 months ago - 1 comment

#1651 - remove optimum-intel version limit

Pull Request - State: closed - Opened by changwangss 4 months ago - 2 comments

#1650 - update ipex api

Pull Request - State: open - Opened by intellinjun 4 months ago - 3 comments

#1649 - Compatibility for other platforms, AMD, etc.

Issue - State: closed - Opened by rain7996 4 months ago - 5 comments

#1648 - Unify the 'iters' and 'calib_iters' in AutoRound config

Pull Request - State: closed - Opened by PenghuiCheng 4 months ago - 1 comment

#1647 - Set lm-eval to 0.4.2

Pull Request - State: closed - Opened by changwangss 4 months ago - 1 comment

#1646 - [pre-commit.ci] pre-commit autoupdate

Pull Request - State: closed - Opened by pre-commit-ci[bot] 4 months ago - 1 comment

#1645 - Clean INC import

Pull Request - State: closed - Opened by changwangss 5 months ago - 1 comment

#1644 - ITREX: release torch 2.3.x version

Issue - State: closed - Opened by casper-hansen 5 months ago - 2 comments

#1643 - question about configuration

Issue - State: open - Opened by menglin0320 5 months ago - 3 comments
Labels: documentation

#1642 - [CI]fix neural engine error

Pull Request - State: closed - Opened by intellinjun 5 months ago - 1 comment

#1641 - Fix Qwen neural speed

Pull Request - State: closed - Opened by changwangss 5 months ago - 3 comments

#1640 - Improve MPT series SQ

Pull Request - State: closed - Opened by changwangss 5 months ago - 5 comments

#1639 - Support phi series SQ

Pull Request - State: closed - Opened by changwangss 5 months ago - 2 comments

#1638 - fix xpu version itrex detect

Pull Request - State: closed - Opened by zhewang1-intc 5 months ago - 1 comment

#1637 - Fix docs online build

Pull Request - State: closed - Opened by changwangss 5 months ago - 1 comment

#1636 - Fix SQ bloom

Pull Request - State: closed - Opened by changwangss 5 months ago - 2 comments

#1635 - update torch version to 2.3.0 in example/requirements.txt

Pull Request - State: closed - Opened by XuehaoSun 5 months ago - 1 comment

#1634 - fix RAG requirements

Pull Request - State: closed - Opened by Liangyx2 5 months ago - 1 comment

#1633 - Bump neural docker base

Pull Request - State: open - Opened by Chris-Sigopt 5 months ago

#1632 - fix codescan

Pull Request - State: closed - Opened by Liangyx2 5 months ago - 1 comment

#1631 - remove unused binary

Pull Request - State: closed - Opened by XuehaoSun 5 months ago - 1 comment

#1630 - ImportError: cannot import name 'WeightOnlyQuantizedLinear' from 'intel_extension_for_pytorch.nn.utils._quantize_convert'

Issue - State: open - Opened by junruizh2021 5 months ago - 2 comments

#1407 - 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.

Issue - State: open - Opened by kranipa 8 months ago - 8 comments

GitHub / intel/intel-extension-for-transformers issues and pull requests