llama.cpp
e68aa10d - vulkan: sort graph to allow more parallel execution (#15850)

Commit
32 days ago
vulkan: sort graph to allow more parallel execution (#15850) * vulkan: sort graph to allow more parallel execution Add a backend proc to allow the backend to modify the graph. The vulkan implementation looks at which nodes depend on each other and greedily reorders them to group together nodes that don't depend on each other. It only reorders the nodes, doesn't change the contents of any of them. With #15489, this reduces the number of synchronizations needed. * call optimize_graph per-split
Author
Parents
Loading