feat: Update llama.cpp

Author: abetlen

llama_cpp/llama_cpp.py

@@ -190,6 +190,7 @@ def _load_shared_library(lib_base_name: str):
 #     LLAMA_FTYPE_MOSTLY_Q2_K_S        = 21, // except 1d tensors
 #     LLAMA_FTYPE_MOSTLY_Q3_K_XS       = 22, // except 1d tensors
 #     LLAMA_FTYPE_MOSTLY_IQ3_XXS       = 23, // except 1d tensors
+#     LLAMA_FTYPE_MOSTLY_IQ1_S         = 24, // except 1d tensors
 
 #     LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file
 # };
@@ -215,6 +216,7 @@ def _load_shared_library(lib_base_name: str):
 LLAMA_FTYPE_MOSTLY_Q2_K_S = 21
 LLAMA_FTYPE_MOSTLY_Q3_K_XS = 22
 LLAMA_FTYPE_MOSTLY_IQ3_XXS = 23
+LLAMA_FTYPE_MOSTLY_IQ1_S = 24
 LLAMA_FTYPE_GUESSED = 1024
 
 # enum llama_rope_scaling_type {