Skip to content

sycl: Try PkgConfig for LevelZero includes / libs - #31076

Merged
Titaniumtown merged 2 commits into
ggml-org:masterfrom
mctylr-gh:mct-sycl-pkgconfig-l0
Nov 1, 2026
Merged

Titaniumtown merged 2 commits into
ggml-org:masterfrom
mctylr-gh:mct-sycl-pkgconfig-l0

Conversation

@mctylr-gh

@mctylr-gh mctylr-gh commented Oct 24, 2026 •

Copy link
Copy Markdown
Contributor

Overview

Issue: #31074 - "Compile bug: [SYCL] Leverl Zero detection / support needs updating"

WIP: This is a first cut at an attempt to make finding the LevelZero development files (includes and linker libraries) find-able with newer oneAPI installations. (2026.1 or 2026.2, not certain)

Improvements and feedback welcome. I'm not a cmake wizard.

Additional information

Requirements

@github-actions github-actions Bot added ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language labels Oct 24, 2026

@arthw arthw left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It's good job!

Thank you!

@arthw arthw left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It's good job!

Thank you!

WIP: This is a first cut at an attempt to make finding the LevelZero
development files (includes and linker libraries) find-able with newer
oneAPI installations. (2026.1 or 2026.2, not certain)

Improvements and feedback welcome. I'm not a cmake wizard.
@mctylr-gh
mctylr-gh force-pushed the mct-sycl-pkgconfig-l0 branch from 9fb978c to a9f4376 Compare October 27, 2026 18:08
@mctylr-gh
mctylr-gh marked this pull request as ready for review October 30, 2026 01:04
@mctylr-gh
mctylr-gh requested a review from a team as a code owner October 30, 2026 01:04
@arthw arthw added the merge ready A maintainer can use this label to indicate that they consider the changes final and ready to merge. label Oct 31, 2026
Comment thread ggml/src/ggml-sycl/CMakeLists.txt Resolved
Comment thread ggml/src/ggml-sycl/CMakeLists.txt Resolved
@Titaniumtown Titaniumtown removed the merge ready A maintainer can use this label to indicate that they consider the changes final and ready to merge. label Nov 1, 2026
Make an explicit find_package(PkgConfig) (built-in), which I thought was
already done, but isn't.

Add/restore the target_compile_definitions for LEVEL_ZERO support via
pkg-config.
@Titaniumtown Titaniumtown changed the title sycl : Try PkgConfig for LevelZero includes / libs sycl: Try PkgConfig for LevelZero includes / libs Nov 1, 2026
@Titaniumtown
Titaniumtown merged commit dde879b into ggml-org:master Nov 1, 2026
31 of 38 checks passed
@mctylr-gh
mctylr-gh deleted the mct-sycl-pkgconfig-l0 branch November 1, 2026 06:53
@mctylr-gh

Copy link
Copy Markdown
Contributor Author

closes #31074

edwardyoon pushed a commit to edwardyoon/focus-llama that referenced this pull request Nov 1, 2026
iki007 added a commit to iki007/llama.cpp that referenced this pull request Nov 4, 2026
…a61c46)

The -X theirs replay of 190 commits onto master 162e2bb dropped upstream's side where both changed a hunk.
This commit sets the 9 files that differ to the one-time merge resolution (73fa61c46), so the tip's tree equals it:
ggml-sycl/fattn-mkl.cpp and fattn-onednn.cpp (ours: upstream's ggml-org#30761 fixes the same strides and per-sequence
offsets as 8e35c17 / a4cc5c9; the replay applied both offsets, ib * nb3 on top of K_batch), ggml-sycl/dmmv.cpp
(upstream's templated launchers, ggml-org#31325, without the three reorder launchers they replace), ggml-sycl/ggml-sycl.cpp
(upstream's comm_exchange pointer, ggml-org#30956, kept next to our host exchange, which returns first for one context),
ggml-sycl/CMakeLists.txt (upstream's pkg-config lookup, ggml-org#31076, our include line in its fallback),
common/speculative.cpp (upstream's DFlash device features, ggml-org#31506, next to our pos_inject; the MTP nextn setters
after is_mem_shared, ggml-org#31356), src/llama-context.cpp (ggml-org#31506's wait before our ubatch loop), src/models/dflash.cpp,
tests/test-backend-ops.cpp.

Assisted-by: Claude Opus 5.5
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants