diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2024-12-15 09:54:21 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-12-15 09:54:21 +0100 |
| commit | 85c5a1a99569ccc00c280835fe3a69b4af02c43b (patch) | |
| tree | da421487d5ddd0467b2bfd6cbbfb2666406c46f1 /ggml/include | |
| parent | 20758edcae65213b2f575b6d23dfea67ad9dd0e0 (diff) | |
BF16_R16 - 16 interleaved bf16 rows (#142)
* Not working bf16_r4
* Adding bf16_r8
Small performance gain compared to bf16 - 258 t/s vs 234 t/s.
I guess, this is still sub-obtimal.
* bf16_rx: Very slightly faster by interleaving 16 rows
258 t/s -> 263 t/s
* Rename bf16_r4 to bf16_r16
We are interleaving 16 rows now.
* Cleanup unused stuff
---------
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 f9ff97a7..7b7fde0d 100644 --- a/ggml/include/ggml.h +++ b/ggml/include/ggml.h @@ -420,6 +420,7 @@ extern "C" { GGML_TYPE_Q6_K_R4 = 214, GGML_TYPE_IQ4_NL_R4 = 220, GGML_TYPE_IQ4_XS_R4 = 223, + GGML_TYPE_BF16_R16 = 230, GGML_TYPE_Q6_0_R4 = 233, GGML_TYPE_IQ2_BN_R4 = 335, GGML_TYPE_IQ4_K_R4 = 339, @@ -493,6 +494,7 @@ extern "C" { GGML_FTYPE_MOSTLY_Q6_K_R4 = 214, // except 1d tensors GGML_FTYPE_MOSTLY_IQ4_NL_R4 = 219, // except 1d tensors GGML_FTYPE_MOSTLY_IQ4_XS_R4 = 222, // except 1d tensors + 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_IQ4_K_R4 = 332, // except 1d tensors |