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

Revert "sycl : add Q2_K reordered MMVQ and ESIMD kernels (#26336)" (#27486)

Browse Source 
This reverts commit ff14356e0c.
This commit is contained in:
Georgi Gerganov
2026-08-21 14:02:03 +03:00
committed by GitHub
parent 5b6ddc9675
commit 7a0e42fd01
8 changed files with 4 additions and 309 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-sycl/quants.hpp
-23
View File
@@ -58,29 +58,6 @@ 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;