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 /include/llama.h | |
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 'include/llama.h')
-rw-r--r-- | include/llama.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/include/llama.h b/include/llama.h index 2fa78879..92234d6c 100644 --- a/include/llama.h +++ b/include/llama.h @@ -184,6 +184,7 @@ extern "C" { LLAMA_FTYPE_MOSTLY_Q8_0_R4 = 207, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q5_0_R4 = 208, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q4_K_R4 = 214, // except 1d tensors + LLAMA_FTYPE_MOSTLY_Q6_K_R4 = 218, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ4_NL_R4 = 225, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ4_XS_R4 = 230, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q6_0_R4 = 235, // except 1d tensors |