| ./main_prefill \ | |
| --template_filename_axmodel "qwen2.5-0.5b-gptq-int4-ax650/qwen2_p128_l%d_together.axmodel" \ | |
| --axmodel_num 24 \ | |
| --tokenizer_type 2 \ | |
| --filename_tokenizer_model "http://127.0.0.1:12345" \ | |
| --bos 0 --eos 0 \ | |
| --filename_post_axmodel "qwen2.5-0.5b-gptq-int4-ax650/qwen2_post.axmodel" \ | |
| --filename_tokens_embed "qwen2.5-0.5b-gptq-int4-ax650/model.embed_tokens.weight.bfloat16.bin" \ | |
| --tokens_embed_num 151936 \ | |
| --tokens_embed_size 896 \ | |
| --use_mmap_load_embed 1 \ | |
| --live_print 1 \ | |
| --continue 1 \ | |
| --prompt "$1" | |