diff options
| author | Iwan Kawrakow <iwan.kawrakow@gmail.com> | 2024-07-29 12:38:46 +0300 |
|---|---|---|
| committer | Kawrakow <48489457+ikawrakow@users.noreply.github.com> | 2024-08-01 09:38:06 +0200 |
| commit | 5d341757bc73efee0deba07a17679a965037753b (patch) | |
| tree | 33db7a06b6b3ae1067a1d3db36192926705c678f /include | |
| parent | 06e255ac9da49cabde466b9ef8b3c09c0f8d8dd1 (diff) | |
iq5_k: Basics
Quantize/dequantize, CUDA dequantize
Diffstat (limited to 'include')
| -rw-r--r-- | include/llama.h | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/include/llama.h b/include/llama.h index 3549d3f3..7bccd4bb 100644 --- a/include/llama.h +++ b/include/llama.h @@ -170,8 +170,9 @@ extern "C" { LLAMA_FTYPE_MOSTLY_Q4_0_8_8 = 35, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ1_BN = 36, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ2_BN = 37, // except 1d tensors - LLAMA_FTYPE_MOSTLY_IQ4_K = 38, // except 1d tensors - LLAMA_FTYPE_MOSTLY_IQ2_K = 39, // except 1d tensors + LLAMA_FTYPE_MOSTLY_IQ2_K = 38, // except 1d tensors + LLAMA_FTYPE_MOSTLY_IQ4_K = 39, // except 1d tensors + LLAMA_FTYPE_MOSTLY_IQ5_K = 40, // except 1d tensors LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file }; |