llama.cpp/ggml
hipudding dd9e377ed8 feat: add multi-stream and operator fusion conflict detection
- Add operator_fusion_enabled flag to ggml_backend_cann_context
- Implement conflict detection in constructor:
  * ACL graph mode disables multi-stream (higher performance)
  * Multi-stream mode disables operator fusion (low benefit)
- Remove multi-stream fusion code (fusion disabled in multi-stream)
- Keep fusion functionality in single-stream mode
- Remove redundant multi_stream_enabled check in graph_compute
- Fix unused variable warning (sync_all_to_stream)
2026-02-06 02:29:02 +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 feat: add multi-stream and operator fusion conflict detection 2026-02-06 02:29:02 +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