whisper.cpp/ggml
Chenguang Li 1d657effe3 CANN: add operator fusion support for ADD + RMS_NORM (llama/17512)
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.
2026-01-14 09:11:59 +02:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (llama/15094) 2025-08-18 20:30:45 +03:00
include vulkan: extend topk_moe to handle sigmoid w/exp_probs_b for nemotron (llama/18295) 2026-01-14 09:11:59 +02:00
src CANN: add operator fusion support for ADD + RMS_NORM (llama/17512) 2026-01-14 09:11:59 +02:00
.gitignore
CMakeLists.txt ggml : bump version to 0.9.5 (ggml/1410) 2025-12-31 18:27:20 +02:00