llama.cpp

c446b2ed - vulkan: Submit once enough matmul work has been recorded (#12406)

vulkan: Submit once enough matmul work has been recorded (#12406) I've been seeing significantly worse performance for tg with flash attention enabled vs disabled, and it seems to be related to the submit heuristic. Change the heuristic to check how many bytes worth of weight matrix are used and flush every 100MB, and ramp up after the first few submits. This seems to resolve the issue, and also increases perf for non-FA a bit.