You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Operating system (e.g. Ubuntu/Windows/MacOS/...): Ubuntu in WSL2
Device (e.g. iPhone 12 Pro, PC+RTX 3090, ...): X86-64 PC
How you installed MLC-LLM (conda, source): python -m pip install --pre -U -f https://mlc.ai/wheels mlc-llm-nightly-rocm61 mlc-ai-nightly-rocm61
How you installed TVM-Unity (pip, source): Cloned with mlc-llm git source
Python version (e.g. 3.10): 3.11
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_GTEST: AUTO
SUMMARIZE: OFF
TVM_DEBUG_WITH_ABI_CHANGE: OFF
USE_IOS_RPC: OFF
USE_MSC: 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
TVM_LOG_BEFORE_THROW: OFF
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_MSCCL: OFF
USE_VITIS_AI: OFF
USE_MLIR: OFF
USE_RCCL: /opt/rocm/
USE_LLVM: /opt/rocm/llvm/bin/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_NCCL: OFF
USE_ROCBLAS: OFF
GIT_COMMIT_HASH: 2912b0fcc0f1812fef2a02794f11786754c87ea2
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: 2024-09-17 14:51:16 -0400
USE_HIPBLAS: ON
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: 17.0.0git
USE_MRVL: OFF
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_FLASHINFER:
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_NVSHMEM: 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: ON
USE_PAPI: OFF
USE_CURAND: OFF
TVM_CXX_COMPILER_PATH: /opt/rh/gcc-toolset-11/root/usr/bin/c++
HIDE_PRIVATE_SYMBOLS: ON
The text was updated successfully, but these errors were encountered:
I have the exact same issue attempting to follow the same guide, with the ROCm 6.2 version, on native Ubuntu 24.04, Python 3.11, both in Conda and with a virtual environment.
🐛 Bug
I have been following the Android tutorial in official docs: https://llm.mlc.ai/docs/deploy/android.html
When performing Step 2. Build Runtime and Model Libraries,
mlc_llm package
command failed with the following output:RuntimeError: Cannot find compilation output, compilation failed
I then ran the same compilation command in gdb, and found that the failure was caused by a segmentation fault in libtvm:
To Reproduce
Steps to reproduce the behavior:
1.Follow the android tutorial, install dependencies, set environment variables, etc..
2.run
mlc_llm package
Expected behavior
Model compiles, and the
./dist/
directory contain outputs as the tutorial states.Environment
conda
, source):python -m pip install --pre -U -f https://mlc.ai/wheels mlc-llm-nightly-rocm61 mlc-ai-nightly-rocm61
pip
, source): Cloned with mlc-llm git sourcepython -c "import tvm; print('\n'.join(f'{k}: {v}' for k, v in tvm.support.libinfo().items()))"
, applicable if you compile models):The text was updated successfully, but these errors were encountered: