-
Couldn't load subscription status.
- Fork 6.4k
enable 28 GGUF test cases on XPU #11404
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
Signed-off-by: YAO Matrix <[email protected]>
Signed-off-by: root <[email protected]>
|
@a-r-r-o-w @DN6 @yiyixuxu, pls help review, thx. |
Signed-off-by: Yao Matrix <[email protected]>
Signed-off-by: Yao Matrix <[email protected]>
|
@a-r-r-o-w @DN6 @yiyixuxu, pls help review, thx. |
|
@bot /style |
|
Style fixes have been applied. View the workflow run here. |
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
below 28 cases all passed.
tests/quantization/gguf/test_gguf.py::AuraFlowGGUFSingleFileTests::test_dequantize_model
tests/quantization/gguf/test_gguf.py::AuraFlowGGUFSingleFileTests::test_dtype_assignment
tests/quantization/gguf/test_gguf.py::AuraFlowGGUFSingleFileTests::test_gguf_linear_layers
tests/quantization/gguf/test_gguf.py::AuraFlowGGUFSingleFileTests::test_gguf_memory_usage
tests/quantization/gguf/test_gguf.py::AuraFlowGGUFSingleFileTests::test_gguf_parameters
tests/quantization/gguf/test_gguf.py::AuraFlowGGUFSingleFileTests::test_keep_modules_in_fp32
tests/quantization/gguf/test_gguf.py::AuraFlowGGUFSingleFileTests::test_pipeline_inference
tests/quantization/gguf/test_gguf.py::FluxGGUFSingleFileTests::test_dequantize_model
tests/quantization/gguf/test_gguf.py::FluxGGUFSingleFileTests::test_dtype_assignment
tests/quantization/gguf/test_gguf.py::FluxGGUFSingleFileTests::test_gguf_linear_layers
tests/quantization/gguf/test_gguf.py::FluxGGUFSingleFileTests::test_gguf_memory_usage
tests/quantization/gguf/test_gguf.py::FluxGGUFSingleFileTests::test_gguf_parameters
tests/quantization/gguf/test_gguf.py::FluxGGUFSingleFileTests::test_keep_modules_in_fp32
tests/quantization/gguf/test_gguf.py::FluxGGUFSingleFileTests::test_pipeline_inference
tests/quantization/gguf/test_gguf.py::SD35LargeGGUFSingleFileTests::test_dequantize_model
tests/quantization/gguf/test_gguf.py::SD35LargeGGUFSingleFileTests::test_dtype_assignment
tests/quantization/gguf/test_gguf.py::SD35LargeGGUFSingleFileTests::test_gguf_linear_layers
tests/quantization/gguf/test_gguf.py::SD35LargeGGUFSingleFileTests::test_gguf_memory_usage
tests/quantization/gguf/test_gguf.py::SD35LargeGGUFSingleFileTests::test_gguf_parameters
tests/quantization/gguf/test_gguf.py::SD35LargeGGUFSingleFileTests::test_keep_modules_in_fp32
tests/quantization/gguf/test_gguf.py::SD35LargeGGUFSingleFileTests::test_pipeline_inference
tests/quantization/gguf/test_gguf.py::SD35MediumGGUFSingleFileTests::test_dequantize_model
tests/quantization/gguf/test_gguf.py::SD35MediumGGUFSingleFileTests::test_dtype_assignment
tests/quantization/gguf/test_gguf.py::SD35MediumGGUFSingleFileTests::test_gguf_linear_layers
tests/quantization/gguf/test_gguf.py::SD35MediumGGUFSingleFileTests::test_gguf_memory_usage
tests/quantization/gguf/test_gguf.py::SD35MediumGGUFSingleFileTests::test_gguf_parameters
tests/quantization/gguf/test_gguf.py::SD35MediumGGUFSingleFileTests::test_keep_modules_in_fp32
tests/quantization/gguf/test_gguf.py::SD35MediumGGUFSingleFileTests::test_pipeline_inference
for
tests/quantization/gguf/test_gguf.py::SD35MediumGGUFSingleFileTests::test_pipeline_inferenceA100 and XPU output are perceptually same.A100
XPU (Ponte Vecchio 1550)