sycl: quantize and reorder the input to q8_1 when reorder is enabled #13826
+120
−28
Conversation
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
Alcpz
reviewed
May 29, 2025
Co-authored-by: Alberto Cabrera Pérez <alberto.cabrera@intel.com>
Alcpz
approved these changes
May 29, 2025
Rbiessy
approved these changes
May 30, 2025
furyhawk
pushed a commit
to furyhawk/llama.cpp
that referenced
this pull request
Jun 6, 2025
…gml-org#13826) * [WIP]: fuse q8 quantization and reorder * wip2: fuse q8 quantization and reorder * working q8 reorder commit * restored common.hpp * remove debug prints * remove unnecessary headers and remove trailing whitespace * Update ggml/src/ggml-sycl/ggml-sycl.cpp Co-authored-by: Alberto Cabrera Pérez <alberto.cabrera@intel.com> --------- Co-authored-by: Alberto Cabrera Pérez <alberto.cabrera@intel.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Description
This PR adds a kernel which quantizes and reorders the input when converting the src1 tensor to the type q8_1, when the reorder optimization is enabled.
All the test cases pass when running with the environment variable
GGML_SYCL_DISABLE_OPTto 0.Performance Data. All performance data has been gathered with the above environment variable set to 0, with 2025.1 toolkit, and with the parameters of llama-bench set to
-ngl 99 -t 8 -r 10.Battlemage
Lunar Lake