issue/961: fix metax init with preload

[Ceng23333]

#961

issue fixed

cpu

lscpu
Architecture:           aarch64
  CPU op-mode(s):       32-bit, 64-bit
  Byte Order:           Little Endian
CPU(s):                 128
  On-line CPU(s) list:  0-127
Vendor ID:              Phytium
  BIOS Vendor ID:       PHYTIUM LTD.
  Model name:           Phytium,S5000C/64
    BIOS Model name:    S5000C
    Model:              0
    Thread(s) per core: 1
    Core(s) per socket: 64
    Socket(s):          2
    Stepping:           0x0
    BogoMIPS:           2000.00
    Flags:              fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm lrcpc dcpop sha3 sm3 s
                        m4 asimddp sha512

gpu

型号：Mars X203
驱动：HPCC Version: 2.32.0.6

性能指标

python examples/jiuge.py --metax --model_path=/data-aisoft/mechdancer/models/9G7B_MHA --max_new_tokens=1024
Namespace(cpu=False, nvidia=False, metax=True, moore=False, iluvatar=False, cambricon=False, model_path='/data-aisoft/mechdancer/models/9G7B_MHA', max_new_tokens=1024, backend='cpp', batch_size=1, prompt='How are you', tp=1, enable_paged_attn=False)
 load weights ......
Processing: model.safetensors
Processing files: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:03<00:00,  3.36s/it]
 load weights over! 3363.4326457977295 ms

<|im_start|>user
How are you<|im_end|>
<|im_start|>assistant
=================== start generate ====================



 Generation completed in 3349.49 ms
 Batchsize=1  Per_Batch_Input_Len=13  Per_Batch_New_Tokens=41

 Prefill TTFT: 0.86ms  Throughput: 15.11tok/s

 Decode  Avg ITL: 62.22ms   Throughput: 16.07tok/s

Hello! I'm doing well, thank you for asking. How about you? Is there anything specific you'd like to talk about or any questions you have? I'm here to help!
total_time: 3406.82 ms

python examples/jiuge.py --metax --model_path=/data-aisoft/mechdancer/models/9G7B_MHA --max_new_tokens=1024 --tp=4
Namespace(cpu=False, nvidia=False, metax=True, moore=False, iluvatar=False, cambricon=False, model_path='/data-aisoft/mechdancer/models/9G7B_MHA', max_new_tokens=1024, backend='cpp', batch_size=1, prompt='How are you', tp=4, enable_paged_attn=False)
 load weights ......
Processing: model.safetensors
Processing files: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:05<00:00,  5.40s/it]
 load weights over! 5415.926456451416 ms

<|im_start|>user
How are you<|im_end|>
<|im_start|>assistant
=================== start generate ====================



 Generation completed in 4345.9 ms
 Batchsize=1  Per_Batch_Input_Len=13  Per_Batch_New_Tokens=27

 Prefill TTFT: 1.83ms  Throughput: 7.1tok/s

 Decode  Avg ITL: 96.73ms   Throughput: 10.34tok/s

Hello! I'm doing well, thank you for asking. How about you? Is there anything I can help you with today?
total_time: 4424.83 ms

python test/bench/test_benchmark.py --metax /data-aisoft/mechdancer/models/9G7B_MHA --bench ceval --subject middle_school_mathematics --num_samples 100 --backend cpp --ndev 1
============================================================
OVERALL RESULTS
============================================================
============================================================
Overall 成绩: 61/100 = 61.00%
Total Latency: 439.86021568998694 seconds
Total Tokens Processed: 25809 tokens
Overall Throughput: 58.68 tokens/s