feat(sycl): make the intel llama.cpp backend self-contained on any host#10991
Draft
jimmykarily wants to merge 1 commit into
Draft
feat(sycl): make the intel llama.cpp backend self-contained on any host#10991jimmykarily wants to merge 1 commit into
jimmykarily wants to merge 1 commit into
Conversation
The SYCL backend shipped an incomplete oneAPI runtime AND relied on a host-provided GPU driver, so it only ran inside the build container. On a bare host it died with "libze_loader.so.1 / libdnnl.so.3: cannot open shared object file", and even with the host's Intel driver installed it SIGSEGV'd during SYCL init when the host driver was built against a newer glibc than the backend's bundled loader (rolling-release distros). package_intel_libs now bundles the complete, coherent oneAPI runtime (the missing MKL ILP64 / sycl_blas / tbb_thread + oneDNN + the dlopen'd UR adapters, plus a sweep of the backend binaries' own direct deps) and the Intel GPU userspace driver (libze_intel_gpu + libigdrcl + IGC + gmm) with its OpenCL ICD manifest, mirroring how package_vulka Mesa. run.sh points the Level Zero / OpenCL loaders at th driver, and install-base-deps.sh installs it in the SYCL Bundling the driver is safe across kernels because it tal i915/xe via the stable DRM UAPI (unlike NVIDIA's kernel-l Validated on Arch (glibc 2.43, i915): the backend loads a an Iris Xe with no host Intel packages installed. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@ant Signed-off-by: Dimitris Karakasilis <dimitris@karakasilis.me>
jimmykarily
force-pushed
the
bundle-intel-sycl-deps
branch
from
July 22, 2026 08:58
2cde77f to
3d2f0b5
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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.
The SYCL backend shipped an incomplete oneAPI runtime AND relied on a host-provided GPU driver, so it only ran inside the build container. On a bare host it died with "libze_loader.so.1 / libdnnl.so.3: cannot open shared object file", and even with the host's Intel driver installed it SIGSEGV'd during SYCL init when the host driver was built against a newer glibc than the backend's bundled loader (rolling-release distros).
package_intel_libs now bundles the complete, coherent oneAPI runtime (the missing MKL ILP64 / sycl_blas / tbb_thread + oneDNN + the dlopen'd UR adapters, plus a sweep of the backend binaries' own direct deps) and the Intel GPU userspace driver (libze_intel_gpu + libigdrcl + IGC + gmm) with its OpenCL ICD manifest, mirroring how package_vulka Mesa. run.sh points the Level Zero / OpenCL loaders at th driver, and install-base-deps.sh installs it in the SYCL Bundling the driver is safe across kernels because it tal i915/xe via the stable DRM UAPI (unlike NVIDIA's kernel-l
Validated on Arch (glibc 2.43, i915): the backend loads a an Iris Xe with no host Intel packages installed.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@ant