I want to run llama with and without vector extension on qemu in ubuntu. i have the latest riscv toolchain and qemu. when i run the code

$ qemu-riscv64 -L /path/to/sysroot/ -cpu rv64,v=true,vlen=256,elen=64,vext_spec=v1.0 ./llama-cli -m ./path/to/model.gguf -p “Anything” -n 50

i get results,

but when i try the

$ qemu-riscv64 -L /path/to/sysroot/ -cpu rv64, ./llama-cli -m ./path/to/model.gguf -p “Anything” -n 50

i get a cpu dump.
i run ubuntu on virtualbox with windows 11 host. do anyone know whats wrong?

i tried to disable hyper v but nothing happend