diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2024-12-18 13:29:25 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-12-18 13:29:25 +0100 |
| commit | 59d742b00fb48a3704f86c16afbb6b4ebcde8e68 (patch) | |
| tree | ed95493397cc9ea45b8f8d897d1200d0b3588a86 /ggml/include/ggml.h | |
| parent | 9b6d14a2991da41af4aa7ef64a712c63b73ad9fe (diff) | |
IQ5_K_R4 (#149)
* iq5_k_r4: Zen4
Much slower than the others.
* iq5_k_r5: WIP
* Minor
* iq5_k_r4: fix AVX2 nrc_y = 1 case
* iq5_k_r4: better Zen4
But TG is still slower than iq5_k
* iq5_k_r4: slightly better AVX2
* iq5_k_r4: NEON
---------
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 77ee0fb9..07142692 100644 --- a/ggml/include/ggml.h +++ b/ggml/include/ggml.h @@ -426,6 +426,7 @@ extern "C" { GGML_TYPE_IQ2_K_R4 = 337, GGML_TYPE_IQ3_K_R4 = 338, GGML_TYPE_IQ4_K_R4 = 339, + GGML_TYPE_IQ5_K_R4 = 340, GGML_TYPE_Q8_K_R8 = 399, GGML_TYPE_COUNT, }; @@ -502,6 +503,7 @@ extern "C" { 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_IQ5_K_R4 = 333, // except 1d tensors GGML_FTYPE_MOSTLY_Q8_K_R8 = 399, // except 1d tensors }; |