[X] I have searched, and there is no existing issue. / 我已经搜索过了,没有相关的 issue。
Describe the bug / 描述这个 bug
量化、编译时发生的异常
TVMError: Check failed: (_len != nullptr) is false: Reshape only expects the input new shape to be either an Expr or an Array of PrimExprs. However, the given new shape is [[1, 1152, 1, 1]]
AttributeError: <class 'tvm.tir.expr.Mul'> has no attribute value.
TVMError: Check failed: (_len != nullptr) is false: Reshape only expects the input new shape to be either an Expr or an Array of PrimExprs. However, the given new shape is [[1, 1152, 1, 1]]
Due to the continuous updates of the original MLC-LLM repo, these changes you have made are recent updates of MLC-LLM. We plan to merge into MLC-LLM so that these modifications will not happen.
Is there an existing issue ? / 是否已有相关的 issue ?
Describe the bug / 描述这个 bug
量化、编译时发生的异常
TVMError: Check failed: (_len != nullptr) is false: Reshape only expects the input new shape to be either an Expr or an Array of PrimExprs. However, the given new shape is [[1, 1152, 1, 1]]
AttributeError: <class 'tvm.tir.expr.Mul'> has no attribute value.
python缺少tqdm、timm、SentencePiece库
To Reproduce / 如何复现
1.对于MiniCPM-V,在按步骤 [ https://github.com/OpenBMB/mlc-MiniCPM/blob/main/README-ZH.md ] 执行至
mlc_chat convert_weight --model-type ${MODEL_TYPE} ./dist/models/${MODEL_NAME}-hf/ --quantization $QUANTIZATION -o dist/$MODEL_NAME/
时,引发
TVMError: Check failed: (_len != nullptr) is false: Reshape only expects the input new shape to be either an Expr or an Array of PrimExprs. However, the given new shape is [[1, 1152, 1, 1]]
2.对于MiniCPM和MiniCPM-V,在按步骤执行至
mlc_chat compile --model-type ${MODEL_TYPE} dist/${MODEL_NAME}/mlc-chat-config.json --device android -o ./dist/libs/${MODEL_NAME}-android.tar
时,引发
AttributeError: <class 'tvm.tir.expr.Mul'> has no attribute value.
3.同上条件及步骤,引发python缺库
Expected behavior / 期望的结果
我希望将这些相关事项写在 [ https://github.com/OpenBMB/mlc-MiniCPM/ ] 的文档里或以其他方式直接修复(因为我在租用云端显卡进行编译时需要多次重复地自行修改代码,深感麻烦)
1.需要修改py文件,位于
引用 https://github.com/OpenBMB/MiniCPM/issues/47
我将其改为
2.需要修改py文件,位于
引用 https://github.com/OpenBMB/mlc-MiniCPM/pull/2
我将其改为
或参考https://github.com/mlc-ai/mlc-llm/blob/main/python/mlc_chat/compiler_pass/estimate_memory_usage.py
3.安装conda环境时需要附带地
仅为提醒,如有错漏还请指出
Screenshots / 截图
无
Environment / 环境
Additional context / 其他信息
无