ggml-org/llama.cpp b12329

on GitHub

CUDA: Optimize prefil via fuse of w_s scale in epilogue MMQ for nvfp4 checkpoints (#26048)

• ggml-cuda: Apply NVFP4 weight scale in MMQ write-back

• ggml-cuda: Fuse mul_mat(_id) + scale into MMQ

• ggml-cuda: Tests for the fused scale

• ggml-cuda: reuse existing graph to test fusion in mmq epiloque

• ggml-cuda: rename test_mul_mat_vec_fusion to test_mul_mat_fusion for consistency

• ggml-cuda: refine comments for clarity on MMQ dispatch and fusion checks in mul_mat functions

• ggml-cuda: refactor fusion checks for mul_mat operations and remove unused function