diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2024-12-11 11:19:00 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-12-11 11:19:00 +0100 |
| commit | e0adb8b1227dd4622a91a5b3680b4af2e36d32f4 (patch) | |
| tree | 38a28c4e8b948d32495a82dddad6e63d894568a6 /include/llama.h | |
| parent | a63a96b5aea031f9dabf1e7c8d5ee28af170e9e7 (diff) | |
Q3_K_R4 (#134)
* q3_k_r4: Zen4 works, but not as good as it should be
238 t/s, so sloghtly slower than q6_k_r4.
* q3_k_r4: NEON
We get PP-512(LLaMA-3.1-8B) = 106.9 t/s.
This is 1.93X faster than q3_K_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 7290f18f..f87d13ff 100644 --- a/include/llama.h +++ b/include/llama.h @@ -183,6 +183,7 @@ extern "C" { LLAMA_FTYPE_MOSTLY_Q4_0_R4 = 202, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q8_0_R4 = 207, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q5_0_R4 = 208, // except 1d tensors + LLAMA_FTYPE_MOSTLY_Q3_K_R4 = 211, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q4_K_R4 = 214, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q5_K_R4 = 216, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q6_K_R4 = 218, // except 1d tensors |