Search results

ipex.optimize bug with torch.no_grad()

Status: Open.

#874 In intel/intel-extension-for-pytorch;

· AdityaKulshrestha opened on Dec 3, 2025

Native API returns: 29 (UR_RESULT_ERROR_INVALID_KERNEL_NAME) when sampling from

Status: Open.

#873 In intel/intel-extension-for-pytorch;

· Nehereus opened on Nov 18, 2025

[question] Do we have a method for 2-bit quantization?

Status: Open.

#872 In intel/intel-extension-for-pytorch;

· xiaohoua opened on Nov 6, 2025

AttributeError: '_OpNamespace' '_C' object has no attribute 'get_cuda_view_from_cpu_tensor' when using vllm serve --cpu-offload-gb

Status: Open.

#869 In intel/intel-extension-for-pytorch;

· NineMeowICT opened on Oct 17, 2025

OSError: [WinError 126] on import with esimd_kernels.dll on new Intel Core Ultra 9 / Arc GPU

Status: Open.

#868 In intel/intel-extension-for-pytorch;

· avg-techie08 opened on Oct 10, 2025

[IMPORTANT] The future of Intel® Extension for PyTorch*

Status: Open.

#867 In intel/intel-extension-for-pytorch;

· tye1 opened on Oct 10, 2025

weight_only_qlinear_prepack_int4 no found

Status: Open.

#864 In intel/intel-extension-for-pytorch;

· legend-7-7 opened on Sep 25, 2025

OSError: libmkl_intel_lp64.so.2 not found after pip install on ChromeOS

Status: Open.

#862 In intel/intel-extension-for-pytorch;

· Gdub662 opened on Sep 21, 2025

Running GGUF models in vLLM CPU (GNR Machine)

Status: Open.

#861 In intel/intel-extension-for-pytorch;

· azhuvath opened on Sep 19, 2025

Float16 inference fails with Llama-3.1-8B-Instruct on EMR (Intel Xeon 8592+) with IPEX enabled

Status: Open.

#857 In intel/intel-extension-for-pytorch;

· ParzvaI opened on Sep 3, 2025

vllm + ipex support AMX now？

Status: Open.

#855 In intel/intel-extension-for-pytorch;

· guixinliu1995 opened on Aug 26, 2025

AttributeError: 'PhiModel' object has no attribute '_use_flash_attention_2' during evaluation with IPEX transformers reference models

Status: Open.

#852 In intel/intel-extension-for-pytorch;

· vinay-murakala opened on Aug 13, 2025