tvm
tvm copied to clipboard
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Prior to this commit, the `LLVMModuleNode` provided a `"get_func_names"` function that would return the names of functions available within the result of `tvm.build`. However, this utility was not preserved across...
### Environment ubuntu 18.04 llvm 13.0.1 cuda 11.7 TensorRT-8.4.1.5 python3.8.2 ### Steps to reproduce 1.build tvm with USE_CUDA ON、 USE_RELAY_DEBUG ON、 USE_TENSORRT_CODEGEN ON USE_TENSORRT_RUNTIME set to tensorrt path 2.cd into...
``` def test_simple(): code = """ #[version = "0.0.5"] def @simple[A, B](%fdd/ddsa: fn(A) -> B, %xs: A) -> B { %fdd/ddsa(%xs) } def @main(%l: Tensor[(5, 5), float32]) -> Tensor[(5, 5),...
This PR bumps FlashInfer version to support manually configure the kernels being built in config.cmake. Prior to this PR, the kernels being built is hardcoded in FlashInfer header files.
Bumps [sqlparse](https://github.com/andialbrecht/sqlparse) from 0.4.3 to 0.5.0. Changelog Sourced from sqlparse's changelog. Release 0.5.0 (Apr 13, 2024) Notable Changes Drop support for Python 3.5, 3.6, and 3.7. Python 3.12 is now...
### Expected behavior Data flows should be evident and unambiguous from the execution graph dumped from TVM debugger. ### Actual behavior Only-reshape node has no ordinal numbers and can not...
Bumps [idna](https://github.com/kjd/idna) from 3.4 to 3.7. Release notes Sourced from idna's releases. v3.7 What's Changed Fix issue where specially crafted inputs to encode() could take exceptionally long amount of time...
Bumps [idna](https://github.com/kjd/idna) from 3.3 to 3.7. Release notes Sourced from idna's releases. v3.7 What's Changed Fix issue where specially crafted inputs to encode() could take exceptionally long amount of time...
When attempting to compile the model after applying LazyGradientInit optimization passes in TVM, an error is encountered: ``` tvm.error.InternalError: Check failed: (it != type_definitions.end()) is false: There is no definition...
Fix https://github.com/apache/tvm/issues/16633 The broken tests are below items of "tests/scripts/task_python_unittest.sh" "tir-transform" "tir-usmp" The crashed cases: tests/python/tir-transform/test_tir_transform_inject_rolling_buffer.py tests/python/tir-usmp/test_tir_usmp_algo.py tests/python/tir-usmp/test_tir_usmp_analysis_extract_bufferinfo.py tests/python/tir-usmp/test_tir_usmp_transform_convert_pool_allocations_to_offsets.py tests/python/tir-usmp/test_tir_usmp_utils.py other failed cases: tests/python/tir-transform/test_tir_transform_pointer_value_type_rewrite.py::TestRewriteToShuffle::test_compare tests/python/tir-transform/test_tir_transform_force_narrow_index_to_i32.py::test_thread_axis2 tests/python/tir-transform/test_tir_transform_hoist_if.py::test_hoisting_block_scope_4 tests/python/tir-transform/test_transform_default_gpu_schedule.py::test_add_on_metal