discuss-archive  

Messages by Date

• 2025/11/24 Re: [PR] [CI] Enhance python linting scripts to support revision-based checks [tvm] via GitHub
• 2025/11/24 Re: [I] [Question] Kindly ask for metal example. [tvm-ffi] via GitHub
• 2025/11/24 Re: [PR] [Feature] Support vanilla C++ STL in FFI. [tvm-ffi] via GitHub
• 2025/11/24 Re: [PR] [Fix] Cast Shape from DLTensor* [tvm-ffi] via GitHub
• 2025/11/24 Re: [I] [Feature Request] Function Overloading [tvm-ffi] via GitHub
• 2025/11/24 Re: [I] [Feature Request] Function Overloading [tvm-ffi] via GitHub
• 2025/11/24 Re: [I] [Bug] Installation process incorrect/not working [tvm] via GitHub
• 2025/11/24 Re: [PR] [Feature] Support vanilla C++ STL in FFI. [tvm-ffi] via GitHub
• 2025/11/24 Re: [PR] [Fix] Cast Shape from DLTensor* [tvm-ffi] via GitHub
• 2025/11/24 [GH] (tvm-ffi/main): Workflow run "CI" failed! GitBox
• 2025/11/24 [PR] [Fix] Cast Shape from DLTensor* [tvm-ffi] via GitHub
• 2025/11/24 Re: [PR] [Fix] Cast Shape from DLTensor* [tvm-ffi] via GitHub
• 2025/11/24 Re: [I] SEGV in functions returning Tensor that outlives the Module [tvm-ffi] via GitHub
• 2025/11/24 Re: [I] [Question] Kindly ask for metal example. [tvm-ffi] via GitHub
• 2025/11/24 Re: [I] [Feature Request] Function Overloading [tvm-ffi] via GitHub
• 2025/11/24 [GH] (tvm/main): Workflow run "CI" is working again! GitBox
• 2025/11/24 [GH] (tvm/main): Workflow run "CI" failed! GitBox
• 2025/11/24 Re: [I] [Docs] The end-to-end optimization tutorial doesn't work on the latest code [tvm] via GitHub
• 2025/11/24 Re: [I] [Feature Request] Function Overloading [tvm-ffi] via GitHub
• 2025/11/24 Re: [PR] [Relax][PyTorch] Add binary operation dtype promotion following PyTorch rules in ExportedProgram frontend [tvm] via GitHub
• 2025/11/24 Re: [PR] [CI] Use glob for `conda/build-environment.yaml` in cache key [tvm] via GitHub
• 2025/11/24 Re: [PR] [Relax][PyTorch] Add binary operation dtype promotion following PyTorch rules in ExportedProgram frontend [tvm] via GitHub
• 2025/11/24 Re: [PR] [TIR][Schedule] Add FuseReductionEpilogue primitive to fuse epilogue … [tvm] via GitHub
• 2025/11/24 Re: [PR] [CI] Use glob for `conda/build-environment.yaml` in cache key [tvm] via GitHub
• 2025/11/24 [GH] (tvm/investigate-macos-ci-error): Workflow run "CI" is working again! GitBox
• 2025/11/24 [GH] (tvm/fix-binary-op-promotion): Workflow run "CI" failed! GitBox
• 2025/11/23 Re: [PR] [Relax] Fix the squeeze operator to behave consistently with torch [tvm] via GitHub
• 2025/11/23 [PR] [CI] Use glob for `conda/build-environment.yaml` in cache key [tvm] via GitHub
• 2025/11/23 [PR] [Relax][PyTorch] Add binary operation dtype promotion following PyTorch rules in ExportedProgram frontend [tvm] via GitHub
• 2025/11/23 [GH] (tvm/main): Workflow run "CI" failed! GitBox
• 2025/11/23 [GH] (tvm/investigate-macos-ci-error): Workflow run "CI" is working again! GitBox
• 2025/11/23 [GH] (tvm-ffi/orcjit): Workflow run "CI" is working again! GitBox
• 2025/11/23 Re: [PR] [Relax][PyTorch] Add `mul` operator in ExportedProgram frontend [tvm] via GitHub
• 2025/11/23 [GH] (tvm-ffi/orcjit): Workflow run "CI" failed! GitBox
• 2025/11/23 [GH] (tvm-ffi/orcjit): Workflow run "CI" failed! GitBox
• 2025/11/23 Re: [I] [Question] Kindly ask for metal example. [tvm-ffi] via GitHub
• 2025/11/23 [GH] (tvm-ffi/orcjit): Workflow run "CI" failed! GitBox
• 2025/11/23 Re: [PR] [Relax][PyTorch] Add `mul` operator in ExportedProgram frontend [tvm] via GitHub
• 2025/11/23 Re: [I] [Question][Feature Request] Provides dispatch primitives based on dtypes. [tvm-ffi] via GitHub
• 2025/11/23 [GH] (tvm/ep-mul-op): Workflow run "CI" failed! GitBox
• 2025/11/23 Re: [PR] [CI] Update `actions/cache` to v4 in setup action [tvm] via GitHub
• 2025/11/23 Re: [PR] [Feature] Support vanilla C++ STL in FFI. [tvm-ffi] via GitHub
• 2025/11/23 Re: [I] [Question] Kindly ask for metal example. [tvm-ffi] via GitHub
• 2025/11/23 Re: [I] [Question] Kindly ask for metal example. [tvm-ffi] via GitHub
• 2025/11/23 Re: [I] [Question] Kindly ask for metal example. [tvm-ffi] via GitHub
• 2025/11/23 [PR] [Relax][PyTorch] Add support for `mul` operator for ExportedProgram frontend [tvm] via GitHub
• 2025/11/23 [GH] (tvm/main): Workflow run "Nightly Docker Update" failed! GitBox
• 2025/11/23 Re: [PR] [Feature] Add cubin launcher utility as an extra header [tvm-ffi] via GitHub
• 2025/11/23 Re: [PR] [Feature] Add cubin launcher utility as an extra header [tvm-ffi] via GitHub
• 2025/11/23 [GH] (tvm/main): Workflow run "CI" failed! GitBox
• 2025/11/23 Re: [PR] Fix BufferError when converting PyTorch models with sparse tensors [tvm] via GitHub
• 2025/11/23 Re: [I] [Bug] BufferError: Can't export tensors with layout other than torch.strided when model contains sparse tensors [tvm] via GitHub
• 2025/11/23 [GH] (tvm/main): Workflow run "CI" is working again! GitBox
• 2025/11/23 Re: [PR] [Feature] Support vanilla C++ STL in FFI. [tvm-ffi] via GitHub
• 2025/11/23 [GH] (tvm/main): Workflow run "CI" failed! GitBox
• 2025/11/23 [GH] (tvm/main): Workflow run "CI" is working again! GitBox
• 2025/11/23 Re: [PR] [Feature] Support vanilla C++ STL in FFI. [tvm-ffi] via GitHub
• 2025/11/23 Re: [PR] [Feature] Support vanilla C++ STL in FFI. [tvm-ffi] via GitHub
• 2025/11/23 Re: [PR] [Relax][PyTorch] Add negative slicing support in `slice_scatter` operation [tvm] via GitHub
• 2025/11/23 Re: [PR] [Relax][PyTorch] Add broadcast support for `copy` operation [tvm] via GitHub
• 2025/11/23 Re: [PR] [CI] Update `actions/cache` to v4 in setup action [tvm] via GitHub
• 2025/11/23 Re: [PR] [Feature] Support vanilla C++ STL in FFI. [tvm-ffi] via GitHub
• 2025/11/23 Re: [PR] [Feature] Support vanilla C++ STL in FFI. [tvm-ffi] via GitHub
• 2025/11/23 [GH] (tvm/add-copy-broadcast-support): Workflow run "CI" failed! GitBox
• 2025/11/23 Re: [PR] [Relax][PyTorch] Add broadcast support for `copy` operation [tvm] via GitHub
• 2025/11/23 Re: [PR] [Relax][PyTorch] Add negative slicing support in `slice_scatter` operation [tvm] via GitHub
• 2025/11/23 [GH] (tvm/scatter-negative-slicing): Workflow run "CI" failed! GitBox
• 2025/11/23 Re: [PR] [CI] Update `actions/cache` to v4 in setup action [tvm] via GitHub
• 2025/11/23 [GH] (tvm/investigate-macos-ci-error): Workflow run "CI" is working again! GitBox
• 2025/11/23 [GH] (tvm/scatter-negative-slicing): Workflow run "CI" failed! GitBox
• 2025/11/23 [GH] (tvm/add-copy-broadcast-support): Workflow run "CI" failed! GitBox
• 2025/11/23 [PR] [CI] Update `actions/cache` to v4 in setup action [tvm] via GitHub
• 2025/11/23 [PR] [Relax][PyTorch] Add negative slicing support in `slice_scatter` operation [tvm] via GitHub
• 2025/11/23 [PR] [Relax][PyTorch] Add broadcast support for copy operation [tvm] via GitHub
• 2025/11/23 Re: [PR] Fix BufferError when converting PyTorch models with sparse tensors [tvm] via GitHub
• 2025/11/23 Re: [PR] Fix BufferError when converting PyTorch models with sparse tensors [tvm] via GitHub
• 2025/11/23 [PR] Fix BufferError when converting PyTorch models with sparse tensors [tvm] via GitHub
• 2025/11/23 [PR] [#17876]Fix TVM crashes with default relax pipeline when opt_level=1: InternalError: Check failed: (slot->value_computed) is false [tvm] via GitHub
• 2025/11/23 [GH] (tvm/main): Workflow run "CI" failed! GitBox
• 2025/11/23 Re: [PR] [Relax][PyTorch] Add `as_strided` operator in ExportedProgram frontend [tvm] via GitHub
• 2025/11/23 [GH] (tvm/add-as_strided-ep): Workflow run "CI" failed! GitBox
• 2025/11/22 Re: [I] [Bug] Installation process incorrect/not working [tvm] via GitHub
• 2025/11/22 Re: [PR] [Relax][PyTorch] Add `as_strided` operator in ExportedProgram frontend [tvm] via GitHub
• 2025/11/22 [GH] (tvm/main): Workflow run "CI" failed! GitBox
• 2025/11/22 [GH] (tvm/main): Workflow run "tvm-bot" is working again! GitBox
• 2025/11/22 Re: [PR] [Relax][PyTorch] Add `as_strided` operator in ExportedProgram frontend [tvm] via GitHub
• 2025/11/22 [GH] (tvm/main): Workflow run "tvm-bot" failed! GitBox
• 2025/11/22 [GH] (tvm/add-as_strided-ep): Workflow run "CI" failed! GitBox
• 2025/11/22 Re: [PR] [Relax][PyTorch] Add `as_strided` operator in ExportedProgram frontend [tvm] via GitHub
• 2025/11/22 [GH] (tvm/add-as_strided-ep): Workflow run "CI" failed! GitBox
• 2025/11/22 Re: [PR] [Relax][PyTorch] Add `as_strided` operator in ExportedProgram frontend [tvm] via GitHub
• 2025/11/22 Re: [PR] [Relax][PyTorch] Add `count_include_pad` support to `avg_pool2d` in PyTorch frontend [tvm] via GitHub
• 2025/11/22 [GH] (tvm/add-as_strided-ep): Workflow run "CI" failed! GitBox
• 2025/11/22 [PR] [Relax][PyTorch] Add support for `as_strided` operator in ExportedProgram frontend [tvm] via GitHub
• 2025/11/22 [GH] (tvm/main): Workflow run "Nightly Docker Update" failed! GitBox
• 2025/11/22 Re: [PR] [Feature] Add cubin launcher utility as an extra header [tvm-ffi] via GitHub
• 2025/11/22 [GH] (tvm/main): Workflow run "CI" failed! GitBox
• 2025/11/22 Re: [I] [Bug] Segmentation fault when converting PyTorch index assignment operation with torch.export [tvm] via GitHub
• 2025/11/22 Re: [PR] [Relax][PyTorch] Enhance index_put support for multi-dimensional indices [tvm] via GitHub
• 2025/11/22 Re: [PR] [Feature] Add cubin launcher utility as an extra header [tvm-ffi] via GitHub
• 2025/11/22 Re: [PR] [Feature] Add cubin launcher utility as an extra header [tvm-ffi] via GitHub
• 2025/11/22 Re: [PR] [Feature] Add cubin launcher utility as an extra header [tvm-ffi] via GitHub
• 2025/11/22 [GH] (tvm/support-count_include_pad-avg_pool2d): Workflow run "CI" failed! GitBox
• 2025/11/22 Re: [I] [Question] Kindly ask for metal example. [tvm-ffi] via GitHub
• 2025/11/22 Re: [PR] [Feature] Add cubin launcher utility as an extra header [tvm-ffi] via GitHub
• 2025/11/22 Re: [PR] [Feature] Add cubin launcher utility as an extra header [tvm-ffi] via GitHub
• 2025/11/22 Re: [PR] [Feature] Add cubin launcher utility as an extra header [tvm-ffi] via GitHub
• 2025/11/22 Re: [PR] [Feature] Add cubin launcher utility as an extra header [tvm-ffi] via GitHub
• 2025/11/22 Re: [PR] [Feature] Add cubin launcher utility as an extra header [tvm-ffi] via GitHub
• 2025/11/22 Re: [PR] [Relax][PyTorch] Add `count_include_pad` support to `avg_pool2d` in ExportedProgram frontend [tvm] via GitHub
• 2025/11/22 Re: [PR] [Relax][PyTorch] Enhance index_put support for multi-dimensional indices [tvm] via GitHub
• 2025/11/22 [PR] [Relax][PyTorch] Enhance handling of unbounded upper bound constraints [tvm] via GitHub
• 2025/11/21 Re: [PR] [Feature] Add cubin launcher utility as an extra header [tvm-ffi] via GitHub
• 2025/11/21 [PR] Enhance index_put support for multi-dimensional indices and broadcasting [tvm] via GitHub
• 2025/11/21 Re: [PR] [Feature] Add cubin launcher utility as an extra header [tvm-ffi] via GitHub
• 2025/11/21 Re: [PR] [Feature] Add cubin launcher utility as an extra header [tvm-ffi] via GitHub
• 2025/11/21 [GH] (tvm-ffi/cubin-loader): Workflow run "CI" is working again! GitBox
• 2025/11/21 Re: [PR] [Feature] Add cubin launcher utility as an extra header [tvm-ffi] via GitHub
• 2025/11/21 [GH] (tvm-ffi/cubin-loader): Workflow run "CI" failed! GitBox
• 2025/11/21 [GH] (tvm-ffi/cubin-loader): Workflow run "CI" failed! GitBox
• 2025/11/21 [GH] (tvm-ffi/cubin-loader): Workflow run "CI" failed! GitBox
• 2025/11/21 [GH] (tvm-ffi/cubin-loader): Workflow run "CI" failed! GitBox
• 2025/11/21 Re: [PR] [Feature] Add cubin launcher utility as an extra header [tvm-ffi] via GitHub
• 2025/11/21 Re: [I] [Bug] InternalError: PermuteDims dimension mismatch when converting scaled_dot_product_attention with 2D inputs [tvm] via GitHub
• 2025/11/21 Re: [PR] [Feature] Add cubin launcher utility as an extra header [tvm-ffi] via GitHub
• 2025/11/21 [PR] [Feature] Add cubin launcher utility as an extra header [tvm-ffi] via GitHub
• 2025/11/21 Re: [PR] [Relax][PyTorch] Add support for gumbel_softmax [tvm] via GitHub
• 2025/11/21 Re: [PR] [Relax][PyTorch] Add support for grid_sample operator [tvm] via GitHub
• 2025/11/21 Re: [PR] [Relax][PyTorch] Fix `batch_norm.default` args handling in ExportedProgram frontend [tvm] via GitHub
• 2025/11/21 [PR] [Relax][PyTorch] Add count_include_pad support to avg_pool2d [tvm] via GitHub
• 2025/11/21 [GH] (tvm/main): Workflow run "pip in /docker/python for certifi - Update #1161509587" failed! GitBox
• 2025/11/21 [GH] (tvm/main): Workflow run "npm_and_yarn in /web for underscore.string - Update #1161509572" failed! GitBox
• 2025/11/21 Re: [PR] [Web] Bump web runtime version 0.23.0-dev1 [tvm] via GitHub
• 2025/11/21 Re: [PR] [TORCH] Fix precise version of f8e8m0 support [tvm-ffi] via GitHub
• 2025/11/21 [GH] (tvm/main): Workflow run "Nightly Docker Update" failed! GitBox
• 2025/11/21 [GH] (tvm-ffi/torch-compact): Workflow run "CI" is working again! GitBox
• 2025/11/21 [GH] (tvm-ffi/torch-compact): Workflow run "CI" failed! GitBox
• 2025/11/21 [GH] (tvm-ffi/torch-compact): Workflow run "CI" failed! GitBox
• 2025/11/21 [GH] (tvm-ffi/torch-compact): Workflow run "CI" failed! GitBox
• 2025/11/21 Re: [I] [Docs] The end-to-end optimization tutorial doesn't work on the latest code [tvm] via GitHub
• 2025/11/21 Re: [PR] [Relax][PyTorch] Add support for grid_sample operator [tvm] via GitHub
• 2025/11/21 Re: [I] [Feature Request] Support for Gumbel Softmax and related stochastic operations in PyTorch frontend [tvm] via GitHub
• 2025/11/21 Re: [I] [Feature Request] Support for Spatial Transformer Network operations in PyTorch frontend [tvm] via GitHub
• 2025/11/21 Re: [PR] [Relax][PyTorch] Add support for gumbel_softmax [tvm] via GitHub
• 2025/11/21 Re: [PR] [Relax][PyTorch] Add dynamic shape support to `torch.ops.aten.sym_size.int` in ExportedProgram frontend [tvm] via GitHub
• 2025/11/21 [PR] [Relax][PyTorch] Fix batch_norm.default in ExportedProgram frontend [tvm] via GitHub
• 2025/11/21 Re: [PR] [TORCH] Fix precise version of f8e8m0 support [tvm-ffi] via GitHub
• 2025/11/21 [GH] (tvm-ffi/torch-compact): Workflow run "CI" failed! GitBox
• 2025/11/21 Re: [PR] [TORCH] Fix precise version of f8e8m0 support [tvm-ffi] via GitHub
• 2025/11/21 [PR] [TORCH] Fix precise version of f8e8m0 support [tvm-ffi] via GitHub
• 2025/11/21 Re: [PR] [CI] Update file patterns for specific linting hooks [tvm] via GitHub
• 2025/11/21 Re: [PR] [Relax][PyTorch] Add support for grid_sample operator [tvm] via GitHub
• 2025/11/21 Re: [PR] [Relax][PyTorch] Add support for gumbel_softmax [tvm] via GitHub
• 2025/11/21 [PR] [Relax][PyTorch] Add dynamic shape support to `torch.ops.aten.sym_size.int` in ExportedProgram frontend [tvm] via GitHub
• 2025/11/21 [PR] [CI] Update file patterns for specific linting hooks [tvm] via GitHub
• 2025/11/21 [PR] Add support for grid_sample operator [tvm] via GitHub
• 2025/11/21 [PR] [Relax][PyTorch] Add support for gumbel_softmax [tvm] via GitHub
• 2025/11/21 [I] [Question] Kindly ask for metal example. [tvm-ffi] via GitHub
• 2025/11/21 Re: [PR] [Feature] Support vanilla C++ STL in FFI. [tvm-ffi] via GitHub
• 2025/11/21 [GH] (tvm/main): Workflow run "Teams" is working again! GitBox
• 2025/11/21 [I] [Docs] The end-to-end optimization tutorial doesn't work on the latest code [tvm] via GitHub
• 2025/11/20 Re: [PR] [Relax][PyTorch] Enable run_ep_decomposition by default [tvm] via GitHub
• 2025/11/20 Re: [PR] [Relax][PyTorch] Add support for `torch.ops.aten.sym_size.int` in ExportedProgram frontend [tvm] via GitHub
• 2025/11/20 Re: [I] [RESULT][VOTE] Release Apache TVM FFI v0.1.3.rc1 [tvm-ffi] via GitHub
• 2025/11/20 Re: [I] [VOTE] Release Apache TVM FFI v0.1.3.rc1 [tvm-ffi] via GitHub
• 2025/11/20 Re: [I] [VOTE] Release Apache TVM FFI v0.1.3.rc1 [tvm-ffi] via GitHub
• 2025/11/20 [I] [RESULT][VOTE] Release Apache TVM FFI v0.1.3.rc1 [tvm-ffi] via GitHub
• 2025/11/20 Re: [PR] [Web] Bump web runtime version 0.23.0-dev1 [tvm] via GitHub
• 2025/11/20 Re: [PR] [Web] Bump web runtime version 0.23.0-dev1 [tvm] via GitHub
• 2025/11/20 [PR] [Web] Bump web runtime version 0.23.0-dev1 [tvm] via GitHub
• 2025/11/20 [GH] (tvm-ffi/main): Workflow run "mainline-only" is working again! GitBox
• 2025/11/20 Re: [PR] [Feature] Support vanilla C++ STL in FFI. [tvm-ffi] via GitHub
• 2025/11/20 Re: [PR] fix: clang tidy issue [tvm-ffi] via GitHub
• 2025/11/20 Re: [PR] [Relax] Fix the squeeze operator to behave consistently with torch [tvm] via GitHub
• 2025/11/20 Re: [PR] fix: clang tidy issue [tvm-ffi] via GitHub
• 2025/11/20 [PR] fix: clang tidy issue [tvm-ffi] via GitHub
• 2025/11/20 [GH] (tvm-ffi/main): Workflow run "mainline-only" failed! GitBox
• 2025/11/20 Re: [PR] feat: Embed metadata for FFI exported functions [tvm-ffi] via GitHub
• 2025/11/20 [GH] (tvm/issue-17798): Workflow run "PR" is working again! GitBox
• 2025/11/20 [GH] (tvm/main): Workflow run "Nightly Docker Update" failed! GitBox
• 2025/11/20 [GH] (tvm-ffi/orcjit): Workflow run "TVM-FFI-OrcJIT CI Tests" failed! GitBox
• 2025/11/20 [GH] (tvm-ffi/orcjit): Workflow run "CI" failed! GitBox
• 2025/11/20 [GH] (tvm-ffi/orcjit): Workflow run "TVM-FFI-OrcJIT CI Tests" failed! GitBox
• 2025/11/20 Re: [PR] [OrcJIT] Add LLVM ORC JIT v2 dynamic object loader addon [tvm-ffi] via GitHub
• 2025/11/20 [GH] (tvm-ffi/orcjit): Workflow run "CI" failed! GitBox
• 2025/11/20 [GH] (tvm/main): Workflow run "pip in /docker/python for certifi - Update #1160439268" failed! GitBox
• 2025/11/20 [GH] (tvm/main): Workflow run "npm_and_yarn in /web for underscore.string - Update #1160439267" failed! GitBox
• 2025/11/20 Re: [PR] [Web] Replace string with TVMFFIByteArray* to avoid memory issues [tvm] via GitHub
• 2025/11/20 Re: [PR] [Docs] Add kernel library guide [tvm-ffi] via GitHub
• 2025/11/20 Re: [PR] [Relax] Fix the squeeze operator to behave consistently with torch [tvm] via GitHub
• 2025/11/20 [GH] (tvm/main): Workflow run "tvm-bot" is working again! GitBox
• 2025/11/20 Re: [PR] [Web] Replace string with TVMFFIByteArray* to avoid memory issues [tvm] via GitHub
• 2025/11/20 [PR] [TIR]: Fix VerifyStream::Verify causes dereferencing an invalid pointer [tvm] via GitHub
• 2025/11/20 Re: [PR] [BugFix][Codegen, CUDA] Fix faulty codegen for FP8 [tvm] via GitHub
• 2025/11/20 Re: [PR] [Relax] Fix the squeeze operator to behave consistently with torch [tvm] via GitHub
• 2025/11/20 Re: [PR] [Relax] Fix the squeeze operator to behave consistently with torch [tvm] via GitHub
• 2025/11/20 [PR] [Relax] Fix the squeeze operator to behave consistently with torch [tvm] via GitHub
• 2025/11/20 [I] [Feature Request] Support for Gumbel Softmax and related stochastic operations in PyTorch frontend [tvm] via GitHub
• 2025/11/20 [GH] (tvm/main): Workflow run "Teams" is working again! GitBox
• 2025/11/20 [I] [Feature Request] Support for sparse matrix multiplication and random number generation in PyTorch frontend [tvm] via GitHub

• Earlier messages
• Later messages