diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2024-12-10 18:13:47 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-12-10 18:13:47 +0100 |
| commit | a63a96b5aea031f9dabf1e7c8d5ee28af170e9e7 (patch) | |
| tree | 01e5c72689e8daa72a53bbe069c8669655187a34 /ggml/include/ggml.h | |
| parent | c819fa651beb20c559f692801819e0447d0ead85 (diff) | |
Q5_K_R4 (#132)
* q5_k_r4: WIP
* q5_k_r4: Zen4 and AVX2
We get PP-512(LLaMA-3.1-8B) = 248.3 t/s on Zen4.
Q5_K_S has PP-512 = 190 t/s.
* q5_k_r4: NEON
We get PP-512(LLaMA-3.1-8B) = 96.1 t/s.
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'ggml/include/ggml.h')
| -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 6486407f..7f766497 100644 --- a/ggml/include/ggml.h +++ b/ggml/include/ggml.h @@ -413,6 +413,7 @@ extern "C" { GGML_TYPE_Q5_0_R4 = 206, GGML_TYPE_Q8_0_R4 = 208, GGML_TYPE_Q4_K_R4 = 212, + GGML_TYPE_Q5_K_R4 = 213, GGML_TYPE_Q6_K_R4 = 214, GGML_TYPE_IQ4_NL_R4 = 220, GGML_TYPE_IQ4_XS_R4 = 223, @@ -481,6 +482,7 @@ extern "C" { GGML_FTYPE_MOSTLY_Q8_0_R4 = 207, // except 1d tensors GGML_FTYPE_MOSTLY_Q5_0_R4 = 208, // except 1d tensors GGML_FTYPE_MOSTLY_Q4_K_R4 = 212, // except 1d tensors + GGML_FTYPE_MOSTLY_Q5_K_R4 = 215, // except 1d tensors 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 |