[Bug] When I turned on vulkan in tvm, the model was incorrectly compiled

[lss0510]

🐛 Bug

When I opened vulkan in tvm and finished tvm compilation, there was an error when I used mlc-llm to compile RedPajama.

To Reproduce

Steps to reproduce the behavior:

1.run python3 -m mlc_llm.build --hf-path RedPajama-INCITE-Chat-3B-v1 --quantization q4f16_1 --target cuda， I get this error： Automatically using target for weight quantization: cuda -keys=cuda,gpu -arch=sm_75 -max_num_threads=1024 -max_shared_memory_per_block=49152 -max_threads_per_block=1024 -registers_per_block=65536 -thread_warp_size=32 Get old param: 0%| | 0/388 [00:00<?, ?tensors/sSegmentation fault (core dumped) | 0/518 [00:00<?, ?tensors/s]

Expected behavior

Environment

• Platform (CUDA):
• Operating system (Ubuntu):
• Device (RTX 2060, ...)
• How you installed MLC-LLM ( source):
• How you installed TVM-Unity ( source):
• Python version (3.8):
• GPU driver version (535.146.02):
• CUDA/cuDNN version (11.7):
• TVM Unity Hash Tag (python -c "import tvm; print('\n'.join(f'{k}: {v}' for k, v in tvm.support.libinfo().items()))", applicable if you compile models):
• USE_NVTX: OFF USE_GTEST: AUTO SUMMARIZE: OFF USE_IOS_RPC: OFF USE_MSC: OFF USE_ETHOSU: OFF CUDA_VERSION: 11.7 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: OFF USE_OPENCL_GTEST: /path/to/opencl/gtest USE_MKL: OFF USE_PT_TVMDSOOP: OFF MLIR_VERSION: NOT-FOUND 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_MLIR: OFF USE_RCCL: OFF USE_LLVM: /ssd/ssli/LLM/clang+llvm-16.0.0-x86_64-linux-gnu-ubuntu-18.04/bin/llvm-config USE_VERILATOR: OFF USE_TF_TVMDSOOP: OFF USE_THREADS: ON USE_MSVC_MT: OFF BACKTRACE_ON_SEGFAULT: OFF USE_GRAPH_EXECUTOR: ON USE_NCCL: OFF USE_ROCBLAS: OFF GIT_COMMIT_HASH: NOT-FOUND USE_VULKAN: /ssd/ssli/LLM/vulkan/1.3.216.0/x86_64 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: NOT-FOUND USE_HEXAGON_SDK: /path/to/sdk USE_BLAS: none USE_ETHOSN: OFF USE_LIBTORCH: OFF USE_RANDOM: ON USE_CUDA: ON 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: 16.0.0 USE_OPENCL: OFF COMPILER_RT_PATH: 3rdparty/compiler-rt RANG_PATH: 3rdparty/rang/include USE_SPIRV_KHR_INTEGER_DOT_PRODUCT: OFF USE_OPENMP: none 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: /usr/bin/c++ HIDE_PRIVATE_SYMBOLS: OFF
• Any other relevant information:

Additional context

[CharlieFRuan]

Hi @lss0510! We migrated to a new workflow for model compilation. The flow under python3 -m mlc_llm.build is no longer maintained and will likely be removed soon.

Checkout the new three-step process: https://llm.mlc.ai/docs/compilation/compile_models.html

[CharlieFRuan]

Closing this one for now. Feel free to open another issue if issues persist!