CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

convert : support non-mxfp4 HF model (#15153)

Browse Source 
* convert : support non-mxfp4 HF model

* rm redundant check

* disable debug check
This commit is contained in:
Xuan-Son Nguyen
2025-08-07 23:26:03 +02:00
committed by GitHub
parent c4f53563df
commit 50aa938901
2 changed files with 17 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-quant.cpp
View File

@@ -999,7 +999,7 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
new_size += llama_tensor_quantize_impl(new_type, f32_data_03, new_data_03, chunk_size, nrows, n_per_row, imatrix_03, workers, nthread_use);
// TODO: temporary sanity check that the F16 -> MXFP4 is lossless
#if 1
#if 0
if (new_type == GGML_TYPE_MXFP4) {
auto * x = f32_data_03;