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. |
||
|---|---|---|
| .. | ||
| android | ||
| backend | ||
| development | ||
| multimodal | ||
| ops | ||
| android.md | ||
| build-riscv64-spacemit.md | ||
| build-s390x.md | ||
| build.md | ||
| docker.md | ||
| function-calling.md | ||
| install.md | ||
| llguidance.md | ||
| multimodal.md | ||
| ops.md | ||