sycl: add missing BF16 conversion support for Intel oneAPI #17780
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
When running FLUX2 models in stable-diffusion.cpp on Intel GPU with oneAPI SYCL backend, this assertion fails:
The issue is that
ggml_get_to_fp32_sycl(),ggml_get_to_fp16_sycl(), andget_to_fp16_nc_sycl()are missing BF16 conversion cases, causing them to returnnullptr.This PR adds the missing BF16 support in
ggml/src/ggml-sycl/convert.cpp. Usessycl::ext::oneapi::bfloat16(Intel oneAPI only, guarded by__INTEL_LLVM_COMPILER).