sycl: Cleanup codepaths in Get Rows in sycl backend #14215
Merged
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
github-actions
bot
added
ggml
Rbiessy
reviewed
Jun 16, 2025
| @@ -277,13 +188,8 @@ void ggml_sycl_op_get_rows(ggml_backend_sycl_context & ctx, ggml_tensor * dst) { | |||
| src1_i32, (float *)dst->data, ctx.stream()); | |||
| break; | |||
| case GGML_TYPE_Q4_0: | |||
| if (ctx.opt_feature.reorder && dst->op == GGML_OP_MUL_MAT) { | |||
There was a problem hiding this comment.
Highlighting it for future reference, the condition dst->op == GGML_OP_MUL_MAT is always false because of this switch:
llama.cpp/ggml/src/ggml-sycl/ggml-sycl.cpp
Lines 3612 to 3614 in 0dbcabd
Rbiessy
approved these changes
Jun 16, 2025
There was a problem hiding this comment.
Pull Request Overview
This PR cleans up the SYCL backend’s Get Rows implementation by removing unused reorder codepaths and simplifying the dispatch logic.
- Eliminates the
k_get_rows_reorderkernel and its host wrapperget_rows_sycl_reorder - Removes the conditional branch for
ctx.opt_feature.reorderin the Q4_0 case - Leaves only the core
k_get_rowsandget_rows_syclpaths for all quantization types
Comments suppressed due to low confidence (1)
ggml/src/ggml-sycl/getrows.cpp:62
- Since
k_get_rows_reorderand its host wrapper have been removed, verify whetherdequantize_kernel_t_reorderis still referenced elsewhere; if not, remove its typedef and related includes to eliminate unused code.
template<int qk, int qr, dequantize_kernel_t_reorder dequantize_kernel_recorder, typename dst_t>
Alcpz
approved these changes
Jun 17, 2025
gabe-l-hart
added a commit
to gabe-l-hart/llama.cpp
that referenced
this pull request
Jun 20, 2025
* mamba2-sync: (24 commits) sync : ggml Add `ggml_roll` (ggml/1274) docs : fix the link to llama.h (ggml-org#14293) CUDA: add conv_2d_transpose (ggml-org#14287) lint : remove trailing whitepace (ggml-org#14304) vocab : prevent tokenizer overflow (ggml-org#14301) sycl: add usage of enqueue_functions extension (ggml-org#14244) Implement GGML_CPU_ALL_VARIANTS for PowerPC (ggml-org#14286) llama : improve sep token handling (ggml-org#14272) cuda : synchronize graph capture and cublas handle destruction (ggml-org#14288) ggml : fix repack work size for mul_mat_id (ggml-org#14292) ggml: Update KleidiAI to v1.9.0 (ggml-org#14277) model : more uniform output id handling (ggml-org#14275) ubatch : new splitting logic (ggml-org#14217) CUDA: add conv_2d_dw (ggml-org#14265) ggml-cpu : remove unnecesary arm feature detection (ggml-org#14281) gguf-py : make sentencepiece optional (ggml-org#14200) server : add server parameters for draft model cache type (ggml-org#13782) build : suppress gcc15 compile warnings (ggml-org#14261) sycl: Cleanup codepaths in Get Rows in sycl backend (ggml-org#14215) ...
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.
This PR removes some dead codepaths and unused functions inside Get Rows implementation in the sycl backend.