diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2024-12-17 10:18:33 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-12-17 10:18:33 +0100 |
| commit | 4ade4c568c331acad22537f7b9519c740c7a06d0 (patch) | |
| tree | 4f80795dd006c19c9e9e418f4813628dcf72decd /ggml/include | |
| parent | d69344f8ea72c6fe6ec16300b939586fa9633e2e (diff) | |
IQ2_K_R4 (#146)
* iq2_k_r4: Zen4
* iq2_k_r4: NEON
* iq2_k_r4: better matrix x vector multiplication on NEON
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'ggml/include')
| -rw-r--r-- | ggml/include/ggml.h | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/ggml/include/ggml.h b/ggml/include/ggml.h index 04831c2f..77ee0fb9 100644 --- a/ggml/include/ggml.h +++ b/ggml/include/ggml.h @@ -423,6 +423,7 @@ extern "C" { GGML_TYPE_BF16_R16 = 230, GGML_TYPE_Q6_0_R4 = 233, GGML_TYPE_IQ2_BN_R4 = 335, + GGML_TYPE_IQ2_K_R4 = 337, GGML_TYPE_IQ3_K_R4 = 338, GGML_TYPE_IQ4_K_R4 = 339, GGML_TYPE_Q8_K_R8 = 399, @@ -498,6 +499,7 @@ extern "C" { GGML_FTYPE_MOSTLY_BF16_R16 = 224, // except 1d tensors GGML_FTYPE_MOSTLY_Q6_0_R4 = 227, // except 1d tensors GGML_FTYPE_MOSTLY_IQ2_BN_R4 = 329, // except 1d tensors + GGML_FTYPE_MOSTLY_IQ2_K_R4 = 330, // except 1d tensors GGML_FTYPE_MOSTLY_IQ3_K_R4 = 331, // except 1d tensors GGML_FTYPE_MOSTLY_IQ4_K_R4 = 332, // except 1d tensors GGML_FTYPE_MOSTLY_Q8_K_R8 = 399, // except 1d tensors |