sync : llama.cpp (#0)

ggerganov · Feb 28, 2024 · 9fb1f17 · 9fb1f17
1 parent a04cf9e
commit 9fb1f17
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 1 deletion.
diff --git 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
@@ -1 +1 @@
-f1a98c52546d009f742bdec2154c2a314ea950a6
+8c0e8f4e73e275756ad69f9c99b26ead085ca9f0