-
Here the include dir is computed incorrectly
https://github.com/intel/intel-xpu-backend-for-triton/blob/f4a6318f077cee697afd8d90cdf63cc96fd868fb/third_party/intel/backend/driver.py#L14
1) it sh…
-
Please update TGI image to 2.0 from 1.4 in all TGI readme files.
I faced issues with Phi-3 model.
-
Encounter this issue while infering with Intel Arc 770.
pip install torch==2.1.0.post2 torchvision==0.16.0.post2 torchaudio==2.1.0.post2 intel-extension-for-pytorch==2.1.30+xpu oneccl_bind_pt==2.1.…
-
After running huggingface benchmarks with subgroup size 16 (https://github.com/intel/intel-xpu-backend-for-triton/actions/runs/9499093865), we saw some cases in which subgroup size 16 reported better …
-
### 🐛 Describe the bug
# AssertionError: RuntimeError not raised
"test_0dim_tensor_overload_exception_xpu",
# RuntimeError: ceil is not supported for complex inputs
"test_autodiff_…
-
XPU backend is a new backend in PyTorch which targets to enabled hardware acceleration on Intel GPUs via sycl. It's being actively worked on at the moment with first set of patches landed in PyTorch u…
-
CI: https://github.com/intel/intel-xpu-backend-for-triton/actions/runs/11290528037/job/31402571029
Logs
```bash
=================================== FAILURES ============================…
-
### 🐛 Describe the bug
# AssertionError: Tensor-likes are not close!
'test_reference_numerics_extremal__refs_acos_xpu_complex64",
"test_reference_numerics_extremal__refs_acosh_xpu_complex64",
"t…
-
After upgrade triton commit pin from `b8c64f64c18d8cac598b3adb355c21e7439c21de`( currently stock Pytorch in used) to `514e4cdf004278c82216364d1f8534b940cd4238` （2.4 release candidate),
We found the …
etaf updated
3 months ago
-
In https://github.com/intel/intel-xpu-backend-for-triton/pull/1195, we changed target triple from `spir64-unknown-unknown` to `spirv64v1.3-unknown-unknown`, since some SPIR-V 1.4 features that are not…