sync : llama.cpp (#0)

diff --git a/examples/common-ggml.cpp b/examples/common-ggml.cpp
index 7a3607546837bb9a60099f9662b53ad1afe57777..53811ad193c8e502c90fb142d55f96cd6ecf9476 100644 (file)
--- a/examples/common-ggml.cpp
+++ b/examples/common-ggml.cpp
@@ -64,10 +64,12 @@ bool ggml_common_quantize_0(
         case GGML_FTYPE_MOSTLY_Q4_1_SOME_F16:
         case GGML_FTYPE_MOSTLY_IQ2_XXS:
         case GGML_FTYPE_MOSTLY_IQ2_XS:
+        case GGML_FTYPE_MOSTLY_IQ2_S:
         case GGML_FTYPE_MOSTLY_IQ3_XXS:
         case GGML_FTYPE_MOSTLY_IQ3_S:
         case GGML_FTYPE_MOSTLY_IQ1_S:
         case GGML_FTYPE_MOSTLY_IQ4_NL:
+        case GGML_FTYPE_MOSTLY_IQ4_XS:
                 {
                     fprintf(stderr, "%s: invalid model type %d\n", __func__, ftype);
                     return false;
@@ -199,10 +201,12 @@ bool ggml_common_quantize_0(
                 case GGML_TYPE_Q8_K:
                 case GGML_TYPE_IQ2_XXS:
                 case GGML_TYPE_IQ2_XS:
+                case GGML_TYPE_IQ2_S:
                 case GGML_TYPE_IQ3_XXS:
                 case GGML_TYPE_IQ3_S:
                 case GGML_TYPE_IQ1_S:
                 case GGML_TYPE_IQ4_NL:
+                case GGML_TYPE_IQ4_XS:
                 case GGML_TYPE_COUNT:
                     {
                         fprintf(stderr, "%s: unsupported quantization type %d (%s)\n", __func__, ttype, ggml_type_name((ggml_type) ttype));

diff --git a/scripts/sync-llama.last b/scripts/sync-llama.last
index 9d75d02c048b83748f886fe09517215088e6ed2f..b21b9cbd0ca56db7b3817085f90dc13d8dc71b9b 100644 (file)
--- a/scripts/sync-llama.last
+++ b/scripts/sync-llama.last
@@ -1 +1 @@
-f1a98c52546d009f742bdec2154c2a314ea950a6
+8c0e8f4e73e275756ad69f9c99b26ead085ca9f0