[Bug] Unexpected Error: The model weight size may be larger than GPU memory size about mlc-llm HOT 5 CLOSED

max_total_sequence_length = int(
        (
            int(gpu_size_bytes) * 0.90
            - params_bytes
            - temp_func_bytes
            - kv_aux_workspace_bytes
            - model_workspace_bytes
            - logit_processor_workspace_bytes
        )
        / kv_bytes_per_token
    )
    print("gpu_size_bytes: {}".format(gpu_size_bytes))
    print("params_bytes: {}".format(params_bytes))
    print("temp_func_bytes: {}".format(temp_func_bytes))
    print("kv_aux_workspace_bytes: {}".format(kv_aux_workspace_bytes))
    print("model_workspace_bytes: {}".format(model_workspace_bytes))
    print("logit_processor_workspace_bytes: {}".format(logit_processor_workspace_bytes))
    print("kv_bytes_per_token: {}".format(kv_bytes_per_token))
    assert max_total_sequence_length > 0, (
        "Cannot estimate KV cache capacity. "
        f"The model weight size {params_bytes} may be larger than GPU memory size {gpu_size_bytes}"
    )

gpu_size_bytes: 16739180544
params_bytes: 1033572352.0
temp_func_bytes: 21852323840
kv_aux_workspace_bytes: 591666136
model_workspace_bytes: 268894528
logit_processor_workspace_bytes: 195999040.0
kv_bytes_per_token: 196609.25

(base) root@orangepi5pro:/home/Allin/mlc-llm-new# mlc_llm serve ./dist/Qwen1.5-1.8B-Chat-q4f16_1-MLC/ --device opencl --model-lib-path /home/Allin/mlc-llm-new/dist/Qwen1.5-1.8B-Chat-q4f16_1-MLC/Qwen1.5-1.8B-Chat-q4f16_1-opencl.so 
[2024-04-28 23:11:54] INFO auto_device.py:76: Found device: opencl:0
[2024-04-28 23:11:54] INFO chat_module.py:379: Using model folder: /home/Allin/mlc-llm-new/dist/Qwen1.5-1.8B-Chat-q4f16_1-MLC
[2024-04-28 23:11:54] INFO chat_module.py:380: Using mlc chat config: /home/Allin/mlc-llm-new/dist/Qwen1.5-1.8B-Chat-q4f16_1-MLC/mlc-chat-config.json
[2024-04-28 23:11:54] INFO chat_module.py:529: Using library model: /home/Allin/mlc-llm-new/dist/Qwen1.5-1.8B-Chat-q4f16_1-MLC/Qwen1.5-1.8B-Chat-q4f16_1-opencl.so
arm_release_ver of this libmali is 'g6p0-01eac0', rk_so_ver is '7'.
gpu_size_bytes: 16739180544
params_bytes: 1033572352.0
temp_func_bytes: 21852323840
kv_aux_workspace_bytes: 118004696
model_workspace_bytes: 33898816
logit_processor_workspace_bytes: 195999040.0
kv_bytes_per_token: 196609.25
Traceback (most recent call last):
  File "/root/miniforge3/bin/mlc_llm", line 33, in <module>
    sys.exit(load_entry_point('mlc-llm', 'console_scripts', 'mlc_llm')())
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/Allin/mlc-llm-new/python/mlc_llm/__main__.py", line 41, in main
    cli.main(sys.argv[2:])
  File "/home/Allin/mlc-llm-new/python/mlc_llm/cli/serve.py", line 75, in main
    serve(
  File "/home/Allin/mlc-llm-new/python/mlc_llm/interface/serve.py", line 43, in serve
    async_engine = engine.AsyncEngine(model_info, kv_cache_config, enable_tracing=enable_tracing)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/Allin/mlc-llm-new/python/mlc_llm/serve/engine.py", line 780, in __init__
    super().__init__("async", models, kv_cache_config, engine_mode, enable_tracing)
  File "/home/Allin/mlc-llm-new/python/mlc_llm/serve/engine_base.py", line 565, in __init__
    kv_cache_config.max_total_sequence_length = _estimate_max_total_sequence_length(
                                                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/Allin/mlc-llm-new/python/mlc_llm/serve/engine_base.py", line 230, in _estimate_max_total_sequence_length
    assert max_total_sequence_length > 0, (
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AssertionError: Cannot estimate KV cache capacity. The model weight size 1033572352.0 may be larger than GPU memory size 16739180544

{
  "model_type": "qwen2",
  "quantization": "q4f16_1",
  "model_config": {
    "hidden_act": "silu",
    "hidden_size": 2048,
    "intermediate_size": 5504,
    "num_attention_heads": 16,
    "num_hidden_layers": 24,
    "num_key_value_heads": 16,
    "rms_norm_eps": 1e-06,
    "rope_theta": 1000000.0,
    "vocab_size": 151936,
    "context_window_size": 4096,
    "prefill_chunk_size": 4096,
    "tensor_parallel_shards": 1,
    "head_dim": 128,
    "dtype": "float32"
  },
  "vocab_size": 151936,
  "context_window_size": 4096,
  "sliding_window_size": -1,
  "prefill_chunk_size": 4096,
  "attention_sink_size": -1,
  "tensor_parallel_shards": 1,
  "mean_gen_len": 128,
  "max_gen_len": 512,
  "shift_fill_factor": 0.3,
  "temperature": 0.7,
  "presence_penalty": 0.0,
  "freq_uency_penalty": 0.0,
  "repetition_penalty": 1.1,
  "top_p": 0.8,
  "conv_template": {
    "name": "mistral_default",
    "system_template": "[INST] {system_message}",
    "system_message": "Always assist with care, respect, and truth. Respond with utmost utility yet securely. Avoid harmful, unethical, prejudiced, or negative content. Ensure replies promote fairness and positivity.",
    "system_prefix_token_ids": [
      1
    ],
    "add_role_after_system_message": true,
    "roles": {
      "user": "<|im_start|>user",
      "assistant": "<|im_start|>assistant"
    },
    "role_templates": {
      "user": "{user_message}",
      "assistant": "{assistant_message}",
      "tool": "{tool_message}"
    },
    "messages": [],
    "seps": [
      "<|im_end|>\n"
    ],
    "role_content_sep": "\n",
    "role_empty_sep": "\n",
    "stop_str": [
      "<|im_end|>"
    ],
    "stop_token_ids": [
      151643
    ],
    "function_string": "",
    "use_function_calling": false
  },
  "pad_token_id": 151643,
  "bos_token_id": 151643,
  "eos_token_id": [
    151645,
    151643
  ],
  "tokenizer_files": [
    "tokenizer.json",
    "vocab.json",
    "merges.txt",
    "tokenizer_config.json",
    "added_tokens.json"
  ],
  "version": "0.1.0"
}