hipudding c1792d58b5 ggml: cann: add graph_optimize for multi-stream parallel preparation ... Implement ggml_backend_cann_graph_optimize function for CANN backend, ported from Vulkan backend (PR #15489 and #15850). Key changes: - Add graph optimization to reorder nodes based on dependency analysis - Group non-dependent nodes together for potential parallel execution - Preserve fusion patterns (RMS_NORM+MUL, MUL_MAT+ADD, ADD+RMS_NORM) - Add GGML_CANN_DISABLE_GRAPH_OPTIMIZE env var to disable optimization This is the first step toward multi-stream parallel execution on Ascend NPU.		2026-02-04 08:37:57 +00:00
..
cann_multi_stream_implementation.md	ggml: cann: add graph_optimize for multi-stream parallel preparation	2026-02-04 08:37:57 +00:00