diff options
Diffstat (limited to 'ggml/src/ggml-common.h')
| -rw-r--r-- | ggml/src/ggml-common.h | 8 |
1 files changed, 8 insertions, 0 deletions
diff --git a/ggml/src/ggml-common.h b/ggml/src/ggml-common.h index 14813161..679353be 100644 --- a/ggml/src/ggml-common.h +++ b/ggml/src/ggml-common.h @@ -499,6 +499,14 @@ typedef struct { } block_iq1_m; static_assert(sizeof(block_iq1_m) == QK_K/8 + QK_K/16 + QK_K/32, "wrong iq1_m block size/padding"); +// 1.75 bpw - blocks of 32 with 4 interleaved rows = 128 quants +typedef struct { + uint8_t qs[16]; // grid index, low 8 bits + uint8_t qh[ 8]; // grid index, high 3 bits + grid shift bits (for two groups of 8) + uint8_t scales[4]; // 4-bit block scales +} block_iq1_m_r4; +static_assert(sizeof(block_iq1_m_r4) == 28, "wrong iq1_m_r4 block size/padding"); + // // Bitnet and TriLM - implemented as 1.625 bpw // |