LLM-Inference/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-08-12 22:31:22 +04:00
Code Issues Packages Projects Releases Wiki Activity

common : add nvfp4 (ggml/0)

Browse Source
This commit is contained in:
Georgi Gerganov
2026-03-16 13:10:15 +02:00
parent d7926e62d4
commit 81ea958719
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/common-ggml.cpp
+2
View File
@@ -73,6 +73,7 @@ bool ggml_common_quantize_0(
case GGML_FTYPE_MOSTLY_IQ1_M:
case GGML_FTYPE_MOSTLY_BF16:
case GGML_FTYPE_MOSTLY_MXFP4:
case GGML_FTYPE_MOSTLY_NVFP4:
{
fprintf(stderr, "%s: invalid model type %d\n", __func__, ftype);
return false;
@@ -213,6 +214,7 @@ bool ggml_common_quantize_0(
case GGML_TYPE_TQ1_0:
case GGML_TYPE_TQ2_0:
case GGML_TYPE_MXFP4:
case GGML_TYPE_NVFP4:
case GGML_TYPE_COUNT:
{
fprintf(stderr, "%s: unsupported quantization type %d (%s)\n", __func__, ttype, ggml_type_name((ggml_type) ttype));