ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-11 06:20:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

iq5_ks: quantize

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-05-15 09:44:37 +03:00
parent 560820cdb4
commit d6eb80d9ee
3 changed files with 8 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
include/llama.h
View File

@@ -193,6 +193,7 @@ extern "C" {
LLAMA_FTYPE_MOSTLY_IQ2_KS = 147, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ4_KSS = 148, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q8_KV = 149, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ5_KS = 150, // except 1d tensors
//
LLAMA_FTYPE_MOSTLY_Q4_0_R8 = 202, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q8_0_R8 = 207, // except 1d tensors
@@ -231,7 +232,7 @@ extern "C" {
LLAMA_ROPE_SCALING_TYPE_LINEAR = 1,
LLAMA_ROPE_SCALING_TYPE_YARN = 2,
LLAMA_ROPE_SCALING_TYPE_LONGROPE = 3,
LLAMA_ROPE_SCALING_TYPE_MAX_VALUE = LLAMA_ROPE_SCALING_TYPE_LONGROPE,
LLAMA_ROPE_SCALING_TYPE_MAX_VALUE = LLAMA_ROPE_SCALING_TYPE_LONGROPE,
};
enum llama_pooling_type {