diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2024-12-18 19:58:21 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-12-18 19:58:21 +0100 |
| commit | dfa12b7f91b9d71bc11f5042151bde949da04d61 (patch) | |
| tree | db8749f2ac908f88189885433907f71e800f1bc0 /include/llama.h | |
| parent | 59d742b00fb48a3704f86c16afbb6b4ebcde8e68 (diff) | |
IQ4_KS_R4 (#150)
* iq4_ks_r4: Zen4
* iq4_ks_r4: AVX2
* iq4_ks_r4: WIP
* iq4_ks_r4: slightly better Zen4
* iq4_ks_r4: slightly better Zen4
* iq4_ks_r4: NEON
* Minor
---------
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 7267fbd4..5480f4e9 100644 --- a/include/llama.h +++ b/include/llama.h @@ -197,6 +197,7 @@ extern "C" { LLAMA_FTYPE_MOSTLY_IQ3_K_R4 = 339, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ4_K_R4 = 340, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ5_K_R4 = 341, // except 1d tensors + LLAMA_FTYPE_MOSTLY_IQ4_KS_R4 = 345, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q8_K_R8 = 399, // except 1d tensors LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file |