ClaudeBot/llama.cpp
0
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-17 20:31:47 +02:00
Code Issues Packages Projects Releases Wiki Activity

AVX2: Speed up large batch size prompt processing of IQ models (#27402)

Browse Source 
* Batched gemm for grid IQ quants

Style updates and a bit more performance

Clean up comments

Move code around

Vectorize IQ panel decode, lower threshold for speedup

IQ panel: single-source gather layout, gate bias, vectorize interleave

Add ggml_gemm_iqp_8x8_q8_K_p4 kernel, remove gather buffer

Move IQ panel code out of repack into iqp.cpp, clean up comments

Another comment sweep

* Add myself as iqp.* codeownder

* Remove ggml_cpu_iqp_scratch_offset and ggml_cpu_iqp_src1_conv_size

* Renaming and moving

* The other half of renaming and moving

* Move macros and ggml_cpu_iqp_mul_mat_id_min_batch definition

* Update ggml/src/ggml-cpu/iqp.h

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Add iqp_rows work buffer

* Revert "Add iqp_rows work buffer"

This reverts commit 425542991e.

* Add NUMA fallback

* Add 10 row batch tests for IQP coverage on all grid IQ types

* Swap assert for return false in support check

* Move IQP mul_mat_id test

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Bartowski
2026-08-31 14:33:50 -04:00
committed by GitHub
co-authored by Georgi Gerganov
parent 2a74817f93
commit 85c55223ca
7 changed files with 1342 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CODEOWNERS
+1
View File
@@ -57,6 +57,7 @@
/ggml/src/ggml-cann/ @ggml-org/ggml-cann
/ggml/src/ggml-common.h @ggerganov
/ggml/src/ggml-cpu/ @ggerganov
/ggml/src/ggml-cpu/iqp.* @bartowski1182
/ggml/src/ggml-cpu/spacemit/ @alex-spacemit
/ggml/src/ggml-cuda/ @ggml-org/ggml-cuda
/ggml/src/ggml-cuda/vendors/hip.h @IMbackK