mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-05-02 07:04:19 +00:00
67e3f6f601
This commit implements operator fusion for ADD + RMS_NORM operations in the CANN backend to reduce memory access overhead and improve performance. The fusion is controlled by the GGML_CANN_OPERATOR_FUSION environment variable (default: false). Changes: - Implement ggml_cann_op_add_rms_norm_fused() using ACLNN AddRmsNorm - Add ggml_cann_can_fuse() to check fusion eligibility - Integrate fusion logic into computation graph evaluation - Add test cases for ADD + RMS_NORM fusion - Update documentation with new environment variable The fusion combines ADD and RMS_NORM into a single kernel call, which is more efficient than executing them separately.