diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2024-12-20 09:12:48 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-12-20 09:12:48 +0100 |
| commit | f4170f78bdfe69050c60bf3b51370d6c97593489 (patch) | |
| tree | 99f68c0b9eeeeba657d80b6c5247d7efee8c840f /ggml/src/ggml-quants.c | |
| parent | dfa12b7f91b9d71bc11f5042151bde949da04d61 (diff) | |
IQ3_XXS_R4 (#153)
* iq3_xxs_r4: 1st shot on Zen4
PP-512: 107 t/s -> 137 t/s
TG-128(1 thread): 2.64 t/s -> 3.44 t/s
* iq4_xxs_r4: WIP
* iq4_xxs_r4: 1st shot at AVX2
Note: there is a bug in the AVX2 implementation for nrc_y = 1
for IQ quants with blocks of 32. I have fixed it for now by
using the nrc_y > 1 implementation (which works) also for nrc_y = 1.
* iq3_xxs_r4: NEON
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'ggml/src/ggml-quants.c')
| -rw-r--r-- | ggml/src/ggml-quants.c | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/ggml/src/ggml-quants.c b/ggml/src/ggml-quants.c index 2b59808b..7821fa79 100644 --- a/ggml/src/ggml-quants.c +++ b/ggml/src/ggml-quants.c @@ -15198,6 +15198,7 @@ bool ggml_validate_row_data(enum ggml_type type, const void * data, size_t nbyte case GGML_TYPE_IQ4_KSS: break; case GGML_TYPE_IQ4_NL_R4: break; case GGML_TYPE_IQ4_XS_R4: break; + case GGML_TYPE_IQ3_XXS_R4: break; case GGML_TYPE_Q4_0_R4: break; case GGML_TYPE_Q5_0_R4: break; case GGML_TYPE_Q6_0_R4: break; |