llama.cpp/ggml
hipudding 93e0c17661 CANN: add CUMSUM and TRI op support, fix graph cache op_params matching
- Implement GGML_OP_CUMSUM using aclnnCumsum
- Implement GGML_OP_TRI with all 4 tri types (LOWER, LOWER_DIAG, UPPER, UPPER_DIAG)
  using Tril/MaskedFillScalar approach to work around CANN sparse-zero bugs
- Fix graph cache to always compare op_params for all ops, not just a whitelist
2026-03-28 06:47:56 +00:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include llama: fix llama-model-saver (#20503) 2026-03-25 12:53:16 +02:00
src CANN: add CUMSUM and TRI op support, fix graph cache op_params matching 2026-03-28 06:47:56 +00:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt ggml : bump version to 0.9.8 (ggml/1442) 2026-03-18 15:17:28 +02:00