mozempk/ggml-org-llama-cpp-mirror
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-11-11 22:32:07 +01:00
Code Issues Packages Projects Releases Wiki Activity

opencl: add optimized q8_0 mm kernel for adreno (#18871)

Browse Source 
* Add Q8_0 OpenCL kernel

Co-authored-by: yunjie <yunjie@qti.qualcomm.com>

* opencl: fix build for non-adreno

* opencl: refactor q8_0

* opencl: enforce subgroup size of 64 for adreno for q8_0

* For A750 and older generations, subgroup size can be 64 or 128.
  This kernel assumes subgroup size 64.

* opencl: suppress warning when adreno kernels are disabled

---------

Co-authored-by: yunjie <yunjie@qti.qualcomm.com>
Co-authored-by: Li He <lih@qti.qualcomm.com>
This commit is contained in:
shaofeiqi
2026-01-30 10:19:27 -08:00
committed by GitHub
co-authored by yunjie Li He
parent d9a2a4bcaa
commit 971facc38e
5 changed files with 819 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-opencl/kernels/cvt.cl
+31
View File
@@ -274,6 +274,37 @@ kernel void kernel_restore_block_q8_0(
}
}
kernel void kernel_restore_block_q8_0_trans(
global uchar * src_q,
global half * src_d,
global block_q8_0 * dst,
uint ne00,
uint ne01
){
uint num_blk_per_row = ne00 / QK8_0;
global block_q8_0 * b = (global block_q8_0 *) dst + get_global_id(0) * num_blk_per_row;
global uchar * q = (global uchar *) src_q + get_global_id(0) * 4; // 4 8-bit packed
global half * d = (global half *) src_d + get_global_id(0);
for (uint blk = 0; blk < num_blk_per_row; blk++) {
b->d = *d;
for (uint i = 0; i < QK8_0; i+=4) {
b->qs[i] = q[0];
b->qs[i+1] = q[1];
b->qs[i+2] = q[2];
b->qs[i+3] = q[3];
q += 4 * ne01; // M stride
}
d += ne01;
b++;
}
}
//------------------------------------------------------------------------------
// kernel_convert_block_q6_K
// Convert the block_q6_K format to 3 separate arrays (AOS -> SOA).