Enable CUDA Graph usage for Nemotron Nano v2 (NemotronH)#16328

ggerganov merged 2 commits intoggml-org:masterggml-org/llama.cpp:masterfrom

anavp-nvidia:hotfix_perf_issues_of_nemotron_nano_v2_9banavp-nvidia/llama.cpp:hotfix_perf_issues_of_nemotron_nano_v2_9bCopy head branch name to clipboard