I followed instructions in mlc-llm/cpp at main · mlc-ai/mlc-llm · GitHub.
When running “python3 build.py --model /mnt/e/llm/vicuna-v1-7b --quantization q3f16_0 --max-seq-len 768”. I got an error:
Check failed: (opt_max_thread_per_block.defined()) is false: max_num_threads is not set for target llvm -keys=cpu