diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2024-12-10 12:26:40 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-12-10 12:26:40 +0100 |
| commit | 361174ee6aee8792b4fbb227b9bc328bf9bd6eb9 (patch) | |
| tree | 887c0cb982664604ef977cdac27657d7c61c88a4 /ggml/src/ggml-quants.c | |
| parent | 3ec193b4856df8e5827b83a8c7686e8498c5e5b8 (diff) | |
Q6_K_R4 (#130)
* Adding q6_k_r4
* q6_k_r4: 1st functional AVX2 version
* q6_k_r4: AVX2 and simple Zen4
"Simple" as in processing 4 instead of 8 rows at once.
On Zen4 we get PP-512(LLaMA-3.1-8B) = 238.3 t/s vs
195.2 t/s for Q6_K. TG-128 @ 1 thread is 7.94 t/s
vs 5.38 t/s for Q6_K.
* q6_k_r4: 1st NEON version
PP-512(LLaMA-3.1-8B) = 78 t/s vs 57.6 t/s for q6_K.
TG-128 is slightly lower rthan q6_K for low number of threads,
becomes very slightly better at 8 threads.
* q6_k_r4: slightly faster NEON
PP-512(LLaMA-3.1-8B) = 83.25 t/s
* q6_k_r4: slightly faster Zen4
238.3 t/s -> 243.2 t/s
---------
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 a4b234c5..67f54da7 100644 --- a/ggml/src/ggml-quants.c +++ b/ggml/src/ggml-quants.c @@ -15203,6 +15203,7 @@ bool ggml_validate_row_data(enum ggml_type type, const void * data, size_t nbyte case GGML_TYPE_Q6_0_R4: break; case GGML_TYPE_Q8_0_R4: break; case GGML_TYPE_Q4_K_R4: break; + case GGML_TYPE_Q6_K_R4: break; case GGML_TYPE_Q4_0_4_4: case GGML_TYPE_Q4_0_4_8: { |