[Bug] raise ValueError("Cannot detect local CUDA GPU target!") ValueError: Cannot detect local CUDA GPU target!

gaonkar-dinesh commented 1 year ago

🐛 Bug

To Reproduce

Steps to reproduce the behavior:

1.python3 -m mlc_llm.build --model "path to custom lora llama model" --target cuda --quantization q4f16_1

Expected behavior

Environment

Platform (CUDA):
Operating system (Ubuntu):
How you installed MLC-LLM (source):
How you installed TVM-Unity (pip):
Python version (3.8.5):
GPU driver version (470):
CUDA/cuDNN version (cuda 11.6):
TVM Unity Hash Tag (python -c "import tvm; print('\n'.join(f'{k}: {v}' for k, v in tvm.support.libinfo().items()))",
USE_GTEST: AUTO SUMMARIZE: OFF USE_IOS_RPC: OFF USE_ETHOSU: CUDA_VERSION: NOT-FOUND USE_LIBBACKTRACE: AUTO DLPACK_PATH: 3rdparty/dlpack/include USE_TENSORRT_CODEGEN: OFF USE_THRUST: OFF USE_TARGET_ONNX: OFF USE_AOT_EXECUTOR: ON BUILD_DUMMY_LIBTVM: OFF USE_CUDNN: OFF USE_TENSORRT_RUNTIME: OFF USE_ARM_COMPUTE_LIB_GRAPH_EXECUTOR: OFF USE_CCACHE: AUTO USE_ARM_COMPUTE_LIB: OFF USE_CPP_RTVM: USE_OPENCL_GTEST: /path/to/opencl/gtest USE_MKL: OFF USE_PT_TVMDSOOP: OFF USE_CLML: OFF USE_STACKVM_RUNTIME: OFF USE_GRAPH_EXECUTOR_CUDA_GRAPH: OFF ROCM_PATH: /opt/rocm USE_DNNL: OFF USE_VITIS_AI: OFF USE_LLVM: llvm-config --ignore-libllvm --link-static USE_VERILATOR: OFF USE_TF_TVMDSOOP: OFF USE_THREADS: ON USE_MSVC_MT: OFF BACKTRACE_ON_SEGFAULT: OFF USE_GRAPH_EXECUTOR: ON USE_ROCBLAS: OFF GIT_COMMIT_HASH: 08f4be767da241d1fe47a654ca588ba6353d8e8a USE_VULKAN: ON USE_RUST_EXT: OFF USE_CUTLASS: OFF USE_CPP_RPC: OFF USE_HEXAGON: OFF USE_CUSTOM_LOGGING: OFF USE_UMA: OFF USE_FALLBACK_STL_MAP: OFF USE_SORT: ON USE_RTTI: ON GIT_COMMIT_TIME: 2023-08-15 21:15:45 -0700 USE_HEXAGON_SDK: /path/to/sdk USE_BLAS: none USE_ETHOSN: OFF USE_LIBTORCH: OFF USE_RANDOM: ON USE_CUDA: OFF USE_COREML: OFF USE_AMX: OFF BUILD_STATIC_RUNTIME: OFF USE_CMSISNN: OFF USE_KHRONOS_SPIRV: OFF USE_CLML_GRAPH_EXECUTOR: OFF USE_TFLITE: OFF USE_HEXAGON_GTEST: /path/to/hexagon/gtest PICOJSON_PATH: 3rdparty/picojson USE_OPENCL_ENABLE_HOST_PTR: OFF INSTALL_DEV: OFF USE_PROFILER: ON USE_NNPACK: OFF LLVM_VERSION: 15.0.7 USE_OPENCL: OFF COMPILER_RT_PATH: 3rdparty/compiler-rt RANG_PATH: 3rdparty/rang/include USE_SPIRV_KHR_INTEGER_DOT_PRODUCT: OFF USE_OPENMP: OFF USE_BNNS: OFF USE_CUBLAS: OFF USE_METAL: OFF USE_MICRO_STANDALONE_RUNTIME: OFF USE_HEXAGON_EXTERNAL_LIBS: OFF USE_ALTERNATIVE_LINKER: AUTO USE_BYODT_POSIT: OFF USE_HEXAGON_RPC: OFF USE_MICRO: OFF DMLC_PATH: 3rdparty/dmlc-core/include INDEX_DEFAULT_I64: ON USE_RELAY_DEBUG: OFF USE_RPC: ON USE_TENSORFLOW_PATH: none TVM_CLML_VERSION: USE_MIOPEN: OFF USE_ROCM: OFF USE_PAPI: OFF USE_CURAND: OFF TVM_CXX_COMPILER_PATH: /opt/rh/gcc-toolset-11/root/usr/bin/c++ HIDE_PRIVATE_SYMBOLS: ON
applicable if you compile models):
Any other relevant information:

Additional context

import tvm dev = tvm.cuda() dev cuda(0) print(dev.exist) False

gaonkar-dinesh commented 1 year ago

it worked, compiled mlc-ai with cuda 11.6

ys-2020 commented 1 year ago

Hi @gaonkar-dinesh , I met the same error. Could you please tell me how did you solve the problem with more details. Thank you!

gaonkar-dinesh commented 1 year ago

Hi @gaonkar-dinesh , I met the same error. Could you please tell me how did you solve the problem with more details. Thank you! @ys-2020 have you compiled mlc with cuda support?

gaonkar-dinesh commented 1 year ago

@ys-2020 For me recompiling MLC with appropriate cuda version solved the issue

mlc-ai / mlc-llm