sleepy/llama.cpp
1
0
Fork 0
Code Issues 8 Pull Requests 1 Actions 98 Packages Projects Releases Wiki Activity

ggml : use 64 bytes aligned tile buffers (#21058)

Browse Source 
| Model                            | Test   |   t/s OLD |   t/s NEW |   Speedup |
|:---------------------------------|:-------|----------:|----------:|----------:|
| qwen35 0.8B BF16                 | pp512  |    584.59 |    595.41 |      1.02 |
| qwen35 0.8B BF16                 | tg128  |     52.23 |     52.82 |      1.01 |
| qwen35 0.8B IQ2_M - 2.7 bpw      | pp512  |    260.64 |    261.70 |      1.00 |
| qwen35 0.8B IQ2_M - 2.7 bpw      | tg128  |     81.17 |     80.89 |      1.00 |
| qwen35 0.8B IQ2_XXS - 2.0625 bpw | pp512  |    302.36 |    302.56 |      1.00 |
| qwen35 0.8B IQ2_XXS - 2.0625 bpw | tg128  |     84.93 |     85.12 |      1.00 |
| qwen35 0.8B IQ3_XXS - 3.0625 bpw | pp512  |    263.22 |    260.01 |      0.99 |
| qwen35 0.8B IQ3_XXS - 3.0625 bpw | tg128  |     80.29 |     78.94 |      0.98 |
| qwen35 0.8B IQ4_NL - 4.5 bpw     | pp512  |    728.65 |    742.09 |      1.02 |
| qwen35 0.8B IQ4_NL - 4.5 bpw     | tg128  |     82.39 |     84.46 |      1.03 |
| qwen35 0.8B IQ4_XS - 4.25 bpw    | pp512  |    681.33 |    677.06 |      0.99 |
| qwen35 0.8B IQ4_XS - 4.25 bpw    | tg128  |     80.18 |     79.28 |      0.99 |
| qwen35 0.8B Q2_K_M               | pp512  |    413.28 |    415.94 |      1.01 |
| qwen35 0.8B Q2_K_M               | tg128  |     81.90 |     82.78 |      1.01 |
| qwen35 0.8B Q3_K_M               | pp512  |    493.17 |    495.08 |      1.00 |
| qwen35 0.8B Q3_K_M               | tg128  |     82.75 |     83.23 |      1.01 |
| qwen35 0.8B Q3_K_S               | pp512  |    429.35 |    427.64 |      1.00 |
| qwen35 0.8B Q3_K_S               | tg128  |     86.69 |     87.02 |      1.00 |
| qwen35 0.8B Q4_0                 | pp512  |    783.46 |    782.32 |      1.00 |
| qwen35 0.8B Q4_0                 | tg128  |     88.23 |     87.90 |      1.00 |
| qwen35 0.8B Q4_1                 | pp512  |    741.71 |    729.76 |      0.98 |
| qwen35 0.8B Q4_1                 | tg128  |     85.44 |     86.01 |      1.01 |
| qwen35 0.8B Q4_K_M               | pp512  |    676.24 |    681.31 |      1.01 |
| qwen35 0.8B Q4_K_M               | tg128  |     76.59 |     77.06 |      1.01 |
| qwen35 0.8B Q4_K_S               | pp512  |    683.12 |    688.81 |      1.01 |
| qwen35 0.8B Q4_K_S               | tg128  |     80.50 |     81.19 |      1.01 |
| qwen35 0.8B Q5_K_M               | pp512  |    635.33 |    642.11 |      1.01 |
| qwen35 0.8B Q5_K_M               | tg128  |     72.07 |     72.49 |      1.01 |
| qwen35 0.8B Q5_K_S               | pp512  |    660.95 |    658.18 |      1.00 |
| qwen35 0.8B Q5_K_S               | tg128  |     72.19 |     72.95 |      1.01 |
| qwen35 0.8B Q6_K                 | pp512  |    647.97 |    638.84 |      0.99 |
| qwen35 0.8B Q6_K                 | tg128  |     72.83 |     72.49 |      1.00 |
| qwen35 0.8B Q8_0                 | pp512  |    805.01 |    785.49 |      0.98 |
| qwen35 0.8B Q8_0                 | tg128  |     70.10 |     70.13 |      1.00 |

Signed-off-by: Adrien Gallouët <angt@huggingface.co>
This commit is contained in:
Adrien Gallouët
2026-04-27 08:30:55 +02:00
committed by GitHub
parent 5594d13224
commit f84270ea10
1 changed files with 16 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cpu/amx/mmq.cpp
+16 -16
View File
@@ -2005,12 +2005,12 @@ void tinygemm_kernel_amx(int M, int N, int KB, const void * RESTRICT _A, const v
const int lda = KB * sizeof(TA);
//const int ldb = KB * sizeof(TB);
static thread_local packed_B_t Tile0[TILE_N * TILE_K];
static thread_local packed_B_t Tile1[TILE_N * TILE_K];
static thread_local int8_t Tile23[TILE_M * TILE_K];
alignas(64) static thread_local packed_B_t Tile0[TILE_N * TILE_K];
alignas(64) static thread_local packed_B_t Tile1[TILE_N * TILE_K];
alignas(64) static thread_local int8_t Tile23[TILE_M * TILE_K];
static thread_local int32_t TileC0[TILE_M * TILE_N * 4];
static thread_local int32_t TileC1[TILE_M * TILE_N * 4];
alignas(64) static thread_local int32_t TileC0[TILE_M * TILE_N * 4];
alignas(64) static thread_local int32_t TileC1[TILE_M * TILE_N * 4];
// double buffering C to interleave avx512 and amx
int32_t * C_cur = TileC0;
@@ -2187,21 +2187,21 @@ void tinygemm_kernel_amx(int M, int N, int KB, const void * RESTRICT _A, const v
const int m1 = std::max(M - TILE_M, 0);
//const int lda = KB * sizeof(TA);
static thread_local int8_t Tile0[TILE_N * TILE_K];
static thread_local int8_t Tile1[TILE_N * TILE_K];
static thread_local int8_t Tile23[TILE_M * TILE_K];
alignas(64) static thread_local int8_t Tile0[TILE_N * TILE_K];
alignas(64) static thread_local int8_t Tile1[TILE_N * TILE_K];
alignas(64) static thread_local int8_t Tile23[TILE_M * TILE_K];
// mat mul result for each group
static thread_local int32_t Tile4[TILE_M * TILE_N];
static thread_local int32_t Tile5[TILE_M * TILE_N];
static thread_local int32_t Tile6[TILE_M * TILE_N];
static thread_local int32_t Tile7[TILE_M * TILE_N];
alignas(64) static thread_local int32_t Tile4[TILE_M * TILE_N];
alignas(64) static thread_local int32_t Tile5[TILE_M * TILE_N];
alignas(64) static thread_local int32_t Tile6[TILE_M * TILE_N];
alignas(64) static thread_local int32_t Tile7[TILE_M * TILE_N];
// sum of each QK_K block, contains 8 groups, int32
static thread_local int32_t Sumi4[TILE_M * TILE_N];
static thread_local int32_t Sumi5[TILE_M * TILE_N];
static thread_local int32_t Sumi6[TILE_M * TILE_N];
static thread_local int32_t Sumi7[TILE_M * TILE_N];
alignas(64) static thread_local int32_t Sumi4[TILE_M * TILE_N];
alignas(64) static thread_local int32_t Sumi5[TILE_M * TILE_N];
alignas(64) static thread_local int32_t Sumi6[TILE_M * TILE_N];
alignas(64) static thread_local int32_t Sumi7[TILE_M * TILE_N];
const int k_group_size = std::is_same<TB, block_q6_K>::value ? 16 : 32;
for (int i = 0; i < KB; ++i) {