llama.cpp/docs/backend
Chenguang Li 67e3f6f601
CANN: add operator fusion support for ADD + RMS_NORM (#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.
2026-01-05 15:38:18 +08:00
..
hexagon ggml-hexagon: create generalized functions for cpu side op (#17500) 2025-12-22 23:13:24 -08:00
BLIS.md make : deprecate (#10514) 2024-12-02 21:22:53 +02:00
CANN.md CANN: add operator fusion support for ADD + RMS_NORM (#17512) 2026-01-05 15:38:18 +08:00
CUDA-FEDORA.md docs: update: improve the Fedoa CUDA guide (#12536) 2025-03-24 11:02:26 +00:00
OPENCL.md doc: clarify that steps also apply to linux for opencl (#18002) 2026-01-04 20:39:25 -08:00
SYCL.md docs: Fix typos in SYCL documentation (#18269) 2025-12-24 17:19:47 +08:00
ZenDNN.md ggml-zendnn : add ZenDNN backend for AMD CPUs (#17690) 2025-12-07 00:13:33 +08:00
zDNN.md ggml-zendnn : add ZenDNN backend for AMD CPUs (#17690) 2025-12-07 00:13:33 +08:00