llama.cpp/ggml
hipudding a19c5a52ec cann: simplify graph optimization by removing operator fusion logic
Remove all operator fusion pattern detection logic from graph optimization
to focus on reducing dependencies between operators in multi-stream scenarios.

Key changes:
- Remove fusion pattern matching for RMS_NORM+MUL, MUL_MAT+ADD, etc.
- Remove match_pattern and keep_pattern helper functions
- Simplify to two-pass approach: real nodes first, then view nodes
- Focus on dependency analysis for better parallelism
- Reduce code complexity by ~47% (235 lines -> 125 lines)

This approach is inspired by the Vulkan backend implementation and
prioritizes multi-stream parallelism over operator fusion, as fusion
provides minimal performance benefits in the CANN backend.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-02-10 06:56:07 +00:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include ggml-virtgpu: make the code thread safe (#19204) 2026-02-04 10:46:18 +08:00
src cann: simplify graph optimization by removing operator fusion logic 2026-02-10 06:56:07 +00:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt Bump cmake max version (needed for Windows on Snapdragon builds) (#19188) 2026-02-01 14:13:38 -08:00