discuss-archive  

Messages by Thread

• [PR] [Runtime][VM] Bounds-check per-parameter byteOffset/nbytes in tensor-cache loader [tvm] via GitHub
  • Re: [PR] [Runtime][VM] Bounds-check per-parameter byteOffset/nbytes in tensor-cache loader [tvm] via GitHub
• [PR] [MetaSchedule][CUDA] Serialize GPU verification on Windows [tvm] via GitHub
  • Re: [PR] [MetaSchedule][CUDA] Serialize GPU verification on Windows [tvm] via GitHub
• [PR] [Tests] Update test_adaptive_pooling_window expected IR for const-int-bound fix [tvm] via GitHub
• [PR] [Fix][Relax][PyTorch] Compare Dynamo output against PyTorch reference [tvm] via GitHub
  • Re: [PR] [Fix][Relax][PyTorch] Compare Dynamo output against PyTorch reference [tvm] via GitHub
  • Re: [PR] [Fix][Relax][PyTorch] Compare Dynamo output against PyTorch reference [tvm] via GitHub
• [PR] [Relax][Frontend][ONNX] Support Modern QDQ opset attributes [tvm] via GitHub
  • Re: [PR] [Relax][Frontend][ONNX] Support Modern QDQ opset attributes [tvm] via GitHub
• [GH] (tvm-ffi/junrushao/2026-07-12/tmp-squashed): Workflow run "CI" failed! GitBox
  • [GH] (tvm-ffi/junrushao/2026-07-12/tmp-squashed): Workflow run "CI" failed! GitBox
  • [GH] (tvm-ffi/junrushao/2026-07-12/tmp-squashed): Workflow run "CI" failed! GitBox
• [PR] feat(ffi)!: expand object, reflection, and dataclass support [tvm-ffi] via GitHub
  • Re: [PR] feat(ffi)!: expand object, reflection, and dataclass support [tvm-ffi] via GitHub
  • Re: [PR] feat(ffi)!: expand object, reflection, and dataclass support [tvm-ffi] via GitHub
  • Re: [PR] feat(ffi)!: expand object, reflection, and dataclass support [tvm-ffi] via GitHub
• [PR] [Fix][Relax][ONNX] Preserve rank-expanding Expand [tvm] via GitHub
  • Re: [PR] [Fix][Relax][ONNX] Preserve rank-expanding Expand [tvm] via GitHub
• [I] [Bug][Relax][ONNX] Expand can drop a rank-expanding broadcast when padded shapes match [tvm] via GitHub
• [PR] build(python)!: require CMake 3.26 for ABI-aware builds [tvm-ffi] via GitHub
  • Re: [PR] build(python)!: require CMake 3.26 for ABI-aware builds [tvm-ffi] via GitHub
  • Re: [PR] build(python)!: require CMake 3.26 for ABI-aware builds [tvm-ffi] via GitHub
• Re: [I] How to call TVM ffi functions from tensorflow? [tvm-ffi] via GitHub
• Re: [PR] [Fix][Relax][TFLite] Use astype for frontend casts [tvm] via GitHub
• [PR] [Fix][Python] Use standard scikit-build directory [tvm] via GitHub
  • Re: [PR] [Fix][Python] Use standard scikit-build directory [tvm] via GitHub
  • Re: [PR] [Fix][Python] Use standard scikit-build directory [tvm] via GitHub
  • Re: [PR] [Fix][Python] Use standard scikit-build directory [tvm] via GitHub
• [PR] [Relax][PyTorch] Use make_tensor in exported program tests [tvm] via GitHub
  • Re: [PR] [Relax][PyTorch] Use make_tensor in exported program tests [tvm] via GitHub
  • Re: [PR] [Relax][PyTorch] Use make_tensor in exported program tests [tvm] via GitHub
• [PR] perf(kernel): optimize Blackwell grouped GEMM primitives [tvm] via GitHub
  • Re: [PR] perf(kernel): optimize Blackwell grouped GEMM primitives [tvm] via GitHub
• [PR] [PYTHON] Find libraries in wheel-tagged build directories [tvm] via GitHub
  • Re: [PR] [PYTHON] Find libraries in wheel-tagged build directories [tvm] via GitHub
  • Re: [PR] [PYTHON] Find libraries in wheel-tagged build directories [tvm] via GitHub
  • Re: [PR] [PYTHON] Find libraries in wheel-tagged build directories [tvm] via GitHub
  • Re: [PR] [PYTHON] Find libraries in wheel-tagged build directories [tvm] via GitHub
  • Re: [PR] [PYTHON] Find libraries in wheel-tagged build directories [tvm] via GitHub
• [GH] (tvm/ci/tirx-localize-hardware-gates): Workflow run "Lint" is working again! GitBox
• [GH] (tvm/ci/tirx-localize-hardware-gates): Workflow run "Lint" failed! GitBox
• [GH] (tvm/relax-onnx-group-normalization): Workflow run "Lint" is working again! GitBox
• [GH] (tvm/relax-onnx-group-normalization): Workflow run "Lint" failed! GitBox
• [I] [CI Problem] test_solution_consistency fails intentionally-nondeterministic check in solve_linear_equations [tvm] via GitHub
• [GH] (tvm/fix-onnx-squeeze-axes-attribute): Workflow run "Lint" is working again! GitBox
• [PR] [CI][Tests] Localize hardware test gates [tvm] via GitHub
  • Re: [PR] [CI][Tests] Localize hardware test gates [tvm] via GitHub
  • Re: [PR] [CI][Tests] Localize hardware test gates [tvm] via GitHub
• [GH] (tvm/issue-19517): Workflow run "Lint" is working again! GitBox
• [GH] (tvm/issue-19517): Workflow run "Lint" failed! GitBox
• [PR] [DLight] Fix GPU reduction ScheduleError on 4D non-last-axis reductions [tvm] via GitHub
  • Re: [PR] [DLight] Fix GPU reduction ScheduleError on 4D non-last-axis reductions [tvm] via GitHub
• [GH] (tvm/patch-1): Workflow run "CI" failed! GitBox
• [PR] [CI] Enable parallel GitHub Actions wheel builds [tvm] via GitHub
  • Re: [PR] [CI] Enable parallel GitHub Actions wheel builds [tvm] via GitHub
  • Re: [PR] [CI] Enable parallel GitHub Actions wheel builds [tvm] via GitHub
  • Re: [PR] [CI] Enable parallel GitHub Actions wheel builds [tvm] via GitHub
• [GH] (tvm/relax-onnx-gather-shape-dynamic-index): Workflow run "Lint" is working again! GitBox
• [GH] (tvm/test_ci): Workflow run "Lint" failed! GitBox
• [PR] [DO NOT MERGE] test ci [tvm] via GitHub
  • Re: [PR] [DO NOT MERGE] test ci [tvm] via GitHub
• [PR] Bump pip from 22.1.1 to 26.1.2 in /docker/python [tvm] via GitHub
  • Re: [PR] Bump pip from 22.1.1 to 26.1.2 in /docker/python [tvm] via GitHub
  • Re: [PR] Bump pip from 22.1.1 to 26.1.2 in /docker/python [tvm] via GitHub
• [GH] (tvm/dependabot/pip/docker/python/pip-26.1.2): Workflow run "Lint" failed! GitBox
  • [GH] (tvm/dependabot/pip/docker/python/pip-26.1.2): Workflow run "Lint" failed! GitBox
• [GH] (tvm/tvm-dev/2026-07-10-fix-cuda-build): Workflow run "Lint" is working again! GitBox
  • [GH] (tvm/tvm-dev/2026-07-10-fix-cuda-build): Workflow run "Lint" is working again! GitBox
• [GH] (tvm/tvm-dev/2026-07-10-fix-cuda-build): Workflow run "Lint" failed! GitBox
  • [GH] (tvm/tvm-dev/2026-07-10-fix-cuda-build): Workflow run "Lint" failed! GitBox
• [PR] [Runtime] Fix CUDA build breaks in fp8 cutlass and thrust [tvm] via GitHub
  • Re: [PR] [Runtime] Fix CUDA build breaks in fp8 cutlass and thrust [tvm] via GitHub
  • Re: [PR] [Runtime] Fix CUDA build breaks in fp8 cutlass and thrust [tvm] via GitHub
  • Re: [PR] [Runtime] Fix CUDA build breaks in fp8 cutlass and thrust [tvm] via GitHub
  • Re: [PR] [Runtime] Fix CUDA build breaks in fp8 cutlass and thrust [tvm] via GitHub
  • Re: [PR] [Runtime] Fix CUDA build breaks in fp8 cutlass and thrust [tvm] via GitHub
  • Re: [PR] [Runtime] Fix CUDA build breaks in fp8 cutlass and thrust [tvm] via GitHub
• [PR] [ORCJIT] Embed liborc_rt into the extension and add orc_rt selector [tvm-ffi] via GitHub
  • Re: [PR] [ORCJIT] Embed liborc_rt into the extension and add orc_rt selector [tvm-ffi] via GitHub
  • Re: [PR] [ORCJIT] Embed liborc_rt into the extension and add orc_rt selector [tvm-ffi] via GitHub
• [GH] (tvm/fix/onnx-batchnorm-mixed-dtype): Workflow run "Lint" is working again! GitBox
• [GH] (tvm/fix/onnx-batchnorm-mixed-dtype): Workflow run "Lint" failed! GitBox
• [PR] [Fix][Relax][ONNX] Cast BatchNorm params to input dtype [tvm] via GitHub
  • Re: [PR] [Fix][Relax][ONNX] Cast BatchNorm params to input dtype [tvm] via GitHub
  • Re: [PR] [Fix][Relax][ONNX] Cast BatchNorm params to input dtype [tvm] via GitHub
  • Re: [PR] [Fix][Relax][ONNX] Cast BatchNorm params to input dtype [tvm] via GitHub
  • Re: [PR] [Fix][Relax][ONNX] Cast BatchNorm params to input dtype [tvm] via GitHub
  • Re: [PR] [Fix][Relax][ONNX] Cast BatchNorm params to input dtype [tvm] via GitHub
• [PR] [ORCJIT] Add test cases for test_string_return [tvm-ffi] via GitHub
  • Re: [PR] [ORCJIT] Add test cases for test_string_return [tvm-ffi] via GitHub
  • Re: [PR] [ORCJIT] Add test cases for test_string_return [tvm-ffi] via GitHub
  • Re: [PR] [ORCJIT] Add test cases for test_string_return [tvm-ffi] via GitHub
  • Re: [PR] [ORCJIT] Add test cases for test_string_return [tvm-ffi] via GitHub
  • Re: [PR] [ORCJIT] Add test cases for test_string_return [tvm-ffi] via GitHub
  • Re: [PR] [ORCJIT] Add test cases for test_string_return [tvm-ffi] via GitHub
  • Re: [PR] [ORCJIT] Add test cases for test_string_return [tvm-ffi] via GitHub
  • Re: [PR] [ORCJIT] Add test cases for test_string_return [tvm-ffi] via GitHub
• [GH] (tvm/fix-arith-const-int-bound-modular-set): Workflow run "Lint" failed! GitBox
  • [GH] (tvm/fix-arith-const-int-bound-modular-set): Workflow run "Lint" failed! GitBox
  • [GH] (tvm/fix-arith-const-int-bound-modular-set): Workflow run "Lint" failed! GitBox
  • [GH] (tvm/fix-arith-const-int-bound-modular-set): Workflow run "Lint" failed! GitBox
  • [GH] (tvm/fix-arith-const-int-bound-modular-set): Workflow run "Lint" failed! GitBox
• [PR] [Arith] Fix const-int-bound modular-set tightening for Mod/FloorMod [tvm] via GitHub
  • Re: [PR] [Arith] Fix const-int-bound modular-set tightening for Mod/FloorMod [tvm] via GitHub
  • Re: [PR] [Arith] Fix const-int-bound modular-set tightening for Mod/FloorMod [tvm] via GitHub
  • Re: [PR] [Arith] Fix const-int-bound modular-set tightening for Mod/FloorMod [tvm] via GitHub
  • Re: [PR] [Arith] Fix const-int-bound modular-set tightening for Mod/FloorMod [tvm] via GitHub
  • Re: [PR] [Arith] Fix const-int-bound modular-set tightening for Mod/FloorMod [tvm] via GitHub
  • Re: [PR] [Arith] Fix const-int-bound modular-set tightening for Mod/FloorMod [tvm] via GitHub
  • Re: [PR] [Arith] Fix const-int-bound modular-set tightening for Mod/FloorMod [tvm] via GitHub
  • Re: [PR] [Arith] Fix const-int-bound modular-set tightening for Mod/FloorMod [tvm] via GitHub
  • Re: [PR] [Arith] Fix const-int-bound modular-set tightening for Mod/FloorMod [tvm] via GitHub
  • Re: [PR] [Arith] Fix const-int-bound modular-set tightening for Mod/FloorMod [tvm] via GitHub
  • Re: [PR] [Arith] Fix const-int-bound modular-set tightening for Mod/FloorMod [tvm] via GitHub
  • Re: [PR] [Arith] Fix const-int-bound modular-set tightening for Mod/FloorMod [tvm] via GitHub
  • Re: [PR] [Arith] Fix const-int-bound modular-set tightening for Mod/FloorMod [tvm] via GitHub
  • Re: [PR] [Arith] Fix const-int-bound modular-set tightening for Mod/FloorMod [tvm] via GitHub
  • Re: [PR] [Arith] Fix const-int-bound modular-set tightening for Mod/FloorMod [tvm] via GitHub
  • Re: [PR] [Arith] Fix const-int-bound modular-set tightening for Mod/FloorMod [tvm] via GitHub
• [I] [Bug] Relax ONNX frontend fails to import mixed-dtype BatchNormalization [tvm] via GitHub
  • Re: [I] [Bug] Relax ONNX frontend fails to import mixed-dtype BatchNormalization [tvm] via GitHub
  • Re: [I] [Bug] Relax ONNX frontend fails to import mixed-dtype BatchNormalization [tvm] via GitHub
• [GH] (tvm/fix-19925-shape-to-tensor-device): Workflow run "Lint" is working again! GitBox
• [GH] (tvm/fix-19925-shape-to-tensor-device): Workflow run "Lint" failed! GitBox
• [I] [Bug][MetaSchedule][CUDA] tune_relax for minimal conv2d aborts during candidate generation on Windows [tvm] via GitHub
• [GH] (tvm/fix/onnx-integer-div-truncation): Workflow run "Lint" is working again! GitBox
  • [GH] (tvm/fix/onnx-integer-div-truncation): Workflow run "Lint" is working again! GitBox
• [GH] (tvm/fix/onnx-integer-div-truncation): Workflow run "Lint" failed! GitBox
• [PR] [Fix][Relax][ONNX] Preserve integer Div truncation during import [tvm] via GitHub
  • Re: [PR] [Fix][Relax][ONNX] Preserve integer Div truncation during import [tvm] via GitHub
  • Re: [PR] [Fix][Relax][ONNX] Preserve integer Div truncation during import [tvm] via GitHub
  • Re: [PR] [Fix][Relax][ONNX] Preserve integer Div truncation during import [tvm] via GitHub
  • Re: [PR] [Fix][Relax][ONNX] Preserve integer Div truncation during import [tvm] via GitHub
• [I] [Bug] Relax ONNX frontend folds integer Div through floating-point division for PrimExpr inputs [tvm] via GitHub
• [GH] (tvm/fix/onnx-topk-indices-int64): Workflow run "Lint" is working again! GitBox
• [GH] (tvm/fix/onnx-topk-indices-int64): Workflow run "Lint" failed! GitBox
  • [GH] (tvm/fix/onnx-topk-indices-int64): Workflow run "Lint" failed! GitBox
• Re: [I] [Bug] Constant folding cannot process onnx model correctly: InternalError: Check failed: pb->value != 0 (0 vs. 0) : Divide by zero [tvm] via GitHub
• [GH] (tvm/fix/onnx-topk-indices-int64): Workflow run "CI" failed! GitBox
• [PR] [Fix][Relax][ONNX] Import TopK indices as int64 [tvm] via GitHub
  • Re: [PR] [Fix][Relax][ONNX] Import TopK indices as int64 [tvm] via GitHub
  • Re: [PR] [Fix][Relax][ONNX] Import TopK indices as int64 [tvm] via GitHub
  • Re: [PR] [Fix][Relax][ONNX] Import TopK indices as int64 [tvm] via GitHub
  • Re: [PR] [Fix][Relax][ONNX] Import TopK indices as int64 [tvm] via GitHub
  • Re: [PR] [Fix][Relax][ONNX] Import TopK indices as int64 [tvm] via GitHub
• [I] [Bug] Relax ONNX frontend imports TopK indices as int32 instead of int64 [tvm] via GitHub
  • Re: [I] [Bug] Relax ONNX frontend imports TopK indices as int32 instead of int64 [tvm] via GitHub
• [I] [Bug] [Relax ONNX front]ONNX frontend import failed with shape graph Concat error [tvm] via GitHub
  • Re: [I] [Bug] [Relax ONNX front]ONNX frontend import failed with shape graph Concat error [tvm] via GitHub
  • Re: [I] [Bug] [Relax ONNX front]ONNX frontend import failed with shape graph Concat error [tvm] via GitHub
  • Re: [I] [Bug] [Relax ONNX front]ONNX frontend import failed with shape graph Concat error [tvm] via GitHub
  • Re: [I] [Bug] [Relax ONNX front]ONNX frontend import failed with shape graph Concat error [tvm] via GitHub
• [GH] (tvm-ffi/orcjit-session-refactor): Workflow run "CI" is working again! GitBox
• [PR] [DLight][CUDA] Fix undefined TX in GEMV broadcast epilogue [tvm] via GitHub
  • Re: [PR] [DLight][CUDA] Fix undefined TX in GEMV broadcast epilogue [tvm] via GitHub
  • Re: [PR] [DLight][CUDA] Fix undefined TX in GEMV broadcast epilogue [tvm] via GitHub
  • Re: [PR] [DLight][CUDA] Fix undefined TX in GEMV broadcast epilogue [tvm] via GitHub
  • Re: [PR] [DLight][CUDA] Fix undefined TX in GEMV broadcast epilogue [tvm] via GitHub
• [PR] [Relax][Frontend][ONNX] Support dynamic index for Gather on shape [tvm] via GitHub
  • Re: [PR] [Relax][Frontend][ONNX] Support dynamic index for Gather on shape [tvm] via GitHub
  • Re: [PR] [Relax][Frontend][ONNX] Support dynamic index for Gather on shape [tvm] via GitHub
  • [PR] [Relax][Frontend][ONNX] Support dynamic index for Gather on shape [tvm] via GitHub
  • Re: [PR] [Relax][Frontend][ONNX] Support dynamic index for Gather on shape [tvm] via GitHub
• [PR] [Fix] Preserve ONNX Squeeze axes attribute for opset < 13 [tvm] via GitHub
  • Re: [PR] [Fix] Preserve ONNX Squeeze axes attribute for opset < 13 [tvm] via GitHub
• [GH] (tvm-ffi/orcjit-session-refactor): Workflow run "CI" failed! GitBox
  • [GH] (tvm-ffi/orcjit-session-refactor): Workflow run "CI" failed! GitBox
  • [GH] (tvm-ffi/orcjit-session-refactor): Workflow run "CI" failed! GitBox
  • [GH] (tvm-ffi/orcjit-session-refactor): Workflow run "CI" failed! GitBox
  • [GH] (tvm-ffi/orcjit-session-refactor): Workflow run "CI" failed! GitBox
  • [GH] (tvm-ffi/orcjit-session-refactor): Workflow run "CI" failed! GitBox
  • [GH] (tvm-ffi/orcjit-session-refactor): Workflow run "CI" failed! GitBox
  • [GH] (tvm-ffi/orcjit-session-refactor): Workflow run "CI" failed! GitBox
• [PR] [ORCJIT] Add shared session and high-level load_module [tvm-ffi] via GitHub
  • Re: [PR] [ORCJIT] Add shared session and high-level load_module [tvm-ffi] via GitHub
  • Re: [PR] [ORCJIT] Add shared session and high-level load_module [tvm-ffi] via GitHub
  • Re: [PR] [ORCJIT] Add shared session and high-level load_module [tvm-ffi] via GitHub
  • Re: [PR] [ORCJIT] Add shared session and high-level load_module [tvm-ffi] via GitHub
  • Re: [PR] [ORCJIT] Add shared session and high-level load_module [tvm-ffi] via GitHub
  • Re: [PR] [ORCJIT] Add shared session and high-level load_module [tvm-ffi] via GitHub
  • Re: [PR] [ORCJIT] Add shared session and high-level load_module [tvm-ffi] via GitHub
  • Re: [PR] [ORCJIT] Add shared session and high-level load_module [tvm-ffi] via GitHub
  • Re: [PR] [ORCJIT] Add shared session and high-level load_module [tvm-ffi] via GitHub
• [I] [Bug][Relax] Import failures on PaddleOCR and FasterRCNN-style models: Squeeze axes, shape Gather, and dynamic TopK [tvm] via GitHub
  • Re: [I] [Bug][Relax] Import failures on PaddleOCR and FasterRCNN-style models: Squeeze axes, shape Gather, and dynamic TopK [tvm] via GitHub
  • Re: [I] [Bug][Relax] Import failures on PaddleOCR and FasterRCNN-style models: Squeeze axes, shape Gather, and dynamic TopK [tvm] via GitHub
• [PR] [Relax][PyTorch] Bind symbolic scalar inputs in from_fx [tvm] via GitHub
  • Re: [PR] [Relax][PyTorch] Bind symbolic scalar inputs in from_fx [tvm] via GitHub
  • Re: [PR] [Relax][PyTorch] Bind symbolic scalar inputs in from_fx [tvm] via GitHub
• [PR] [ARITH] Scope interval constraints to mapped variables [tvm] via GitHub
  • Re: [PR] [ARITH] Scope interval constraints to mapped variables [tvm] via GitHub
  • Re: [PR] [ARITH] Scope interval constraints to mapped variables [tvm] via GitHub
  • Re: [PR] [ARITH] Scope interval constraints to mapped variables [tvm] via GitHub
  • Re: [PR] [ARITH] Scope interval constraints to mapped variables [tvm] via GitHub
• [PR] [Arith] Fix dom_map var leak in IntervalSet relaxation [tvm] via GitHub
  • Re: [PR] [Arith] Fix dom_map var leak in IntervalSet relaxation [tvm] via GitHub
  • Re: [PR] [Arith] Fix dom_map var leak in IntervalSet relaxation [tvm] via GitHub
  • Re: [PR] [Arith] Fix dom_map var leak in IntervalSet relaxation [tvm] via GitHub
  • Re: [PR] [Arith] Fix dom_map var leak in IntervalSet relaxation [tvm] via GitHub

• Earlier messages