Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

sycl : add Q2_K reordered MMVQ and ESIMD kernels (again) (#27490)

Browse Source 
* Revert "Revert "sycl : add Q2_K reordered MMVQ and ESIMD kernels (#26336)" (#…"

This reverts commit 7a0e42fd01.

* add gate params
This commit is contained in:
Sigbjørn Skjæret
2026-08-22 10:09:26 +03:00
committed by GitHub
parent 3aeb924628
commit 8672290039
8 changed files with 310 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-sycl/quants.hpp
+23
View File
@@ -58,6 +58,29 @@ template <> struct block_q_t<GGML_TYPE_Q4_0> {
static constexpr int block_to_q8_1_ratio() { return traits::qk / QK8_1; }
};
template <> struct block_q_t<GGML_TYPE_Q2_K> {
struct traits {
static constexpr uint32_t qk = QK_K;
static constexpr uint32_t qi = QI2_K;
static constexpr uint32_t qr = QR2_K;
static constexpr uint32_t vdr_mmvq = 1;
};
// Reordered layout: [qs (QK_K/4 per block)] [scales (QK_K/16 per block)] [dm]
static constexpr std::pair<int, int> get_block_offset(const int block_index, const int /* n_blocks */) {
return { block_index * (QK_K / 4), 0 };
}
static constexpr std::pair<int, int> get_d_offset(int nrows, int ncols, const int block_index) {
auto nblocks = (nrows * (ncols / QK_K));
auto total_qs_bytes = nblocks * (QK_K / 4);
return { total_qs_bytes + block_index * (QK_K / 16),
total_qs_bytes + nblocks * (QK_K / 16) + block_index * sizeof(ggml_half2) };
}
static constexpr int block_to_q8_1_ratio() { return traits::qk / QK8_1; }
};
template <> struct block_q_t<GGML_TYPE_Q3_K> {
struct traits {
static constexpr uint32_t qk = QK_K;