Messages by Thread
-
[GH] (tvm-ffi/junrus/2026-04-10/fix-pyclass-init): Workflow run "CI" is working again!
GitBox
-
[GH] (tvm-ffi/junrus/2026-04-10/fix-pyclass-init): Workflow run "CI" failed!
GitBox
-
[PR] fix(py_class): support `super().__init__()` in `init=False` subclasses [tvm-ffi]
via GitHub
-
[PR] [BugFix][Relax] Select target-specific pipeline in tvm.compile when target is provided [tvm]
via GitHub
-
[PR] [BugFix][TIRx] Fix VerifyMemory crash for PrimFuncs without target attribute [tvm]
via GitHub
-
[PR] [BugFix][MetaSchedule] Fix compile_relax to apply MetaScheduleApplyDatabase after FuseOps [tvm]
via GitHub
-
[PR] [BugFix][TIRx] Fix bad-optional-access in BF16/FP8 legalize passes for target-less PrimFuncs [tvm]
via GitHub
-
[PR] [Relax][TFLite] Fix and test DEPTH_TO_SPACE/SPACE_TO_DEPTH, SELECT ops [tvm]
via GitHub
-
[PR] [BugFix][TOPI] Fix get_const_tuple hanging indefinitely when passed a te.Tensor [tvm]
via GitHub
-
[PR] [Docs] Add API reference for tvm.arith, tvm.testing, tvm.exec, tvm.tirx.backend and extend topi/contrib/ir/target docs [tvm]
via GitHub
-
[GH] (tvm-ffi/cherry-pick/c-class-warn-missing-annotations): Workflow run "CI" is working again!
GitBox
-
[PR] feat(c_class): warn when reflected fields lack Python type annotations [tvm-ffi]
via GitHub
-
[GH] (tvm-ffi/cherry-pick/c-class-warn-missing-annotations): Workflow run "CI" failed!
GitBox
-
[PR] chore(skill): Add skills to better develop with TVM-FFI [tvm-ffi]
via GitHub
-
[PR] fix(cython): Segfault in free-threaded Py_DecRef Cleanup [tvm-ffi]
via GitHub
-
[I] [Bug] Segfault in Free-Threaded Python 3.14t [tvm-ffi]
via GitHub
-
[PR] [Docs] Complete API reference for tvm.relax backend and testing modules [tvm]
via GitHub
-
[PR] [S-TIR] Fix the ScheduleError from missing guard in CheckInline [tvm]
via GitHub
-
[PR] [BugFix][Relax] Fix ONNX get_converter index underflow for old opsets [tvm]
via GitHub
-
[PR] [BugFix][Relax] Fix ONNX Clip converter for opset 11-12 [tvm]
via GitHub
-
[PR] [DLight] Add CPU Reduction schedule rule for softmax-like operators [tvm]
via GitHub
-
[PR] [BugFix][Test][TFLite] Fix and test PAD/PADV2/MIRROR_PAD/TOPK_V2/ONE_HOT converters [tvm]
via GitHub
-
[PR] [relax][frontend][tflite] Add tests for l2_normalization/slice/reverse_v2 [tvm]
via GitHub
-
[PR] [relax][frontend][tflite] Add tests for fully_connected/depthwise_conv2d/transpose_conv/l2_pool2d [tvm]
via GitHub
-
[GH] (tvm-ffi/mc): Workflow run "CI" is working again!
GitBox
-
[GH] (tvm-ffi/mc): Workflow run "CI" failed!
GitBox
-
[PR] [OrcJIT] Arena JITLinkMemoryManager with GOTPCRELX fix (Linux) [tvm-ffi]
via GitHub
-
[PR] [Relax][TFLite] Add test coverage for Reduction operations (#18971) [tvm]
via GitHub
-
[PR] [Docs] Add API reference for tvm.s_tir submodules: dlight, meta_schedule, backend [tvm]
via GitHub
-
[PR] [BugFix] Align tir.round to ties-to-even across all backends [tvm]
via GitHub
-
[PR] Revert "build(deps): replace cmake version exclusion with uv exclude-newer" [tvm-ffi]
via GitHub
-
[PR] build(deps): replace cmake version exclusion with uv exclude-newer [tvm-ffi]
via GitHub
-
Re: [I] [Bug] ONNX Round tie-breaking mismatch on 0.5: TVM lowers to llvm.round (ties-away-from-zero) so Round(sigmoid(0))=1, while ONNX spec requires Round(0.5)=0 (ties-to-even) [tvm]
via GitHub
-
[I] [RESULT][VOTE] Release Apache TVM FFI v0.1.10-rc2 [tvm-ffi]
via GitHub
-
[PR] chore(release): Version bump after release v0.1.10 [tvm-ffi]
via GitHub
-
Re: [I] [Bug] [FRONTEND][ONNX] Error converting operator ConvTranspose: InternalError: In Op(relax.add), the first input shape at dim 1 is T.int64(16) and the second input shape at dim 1 is T.int64(32), which are not broadcastable. [tvm]
via GitHub
-
[PR] [BugFix][ONNX] Fix Round op to use ties-to-even (banker's rounding) [tvm]
via GitHub
-
[PR] [Docs] Add API reference documentation for tvm.script module [tvm]
via GitHub
-
[PR] [Test][TFLite] Add unit tests for RESIZE_BILINEAR and RESIZE_NEAREST_NEIGHBOR ops [tvm]
via GitHub
-
[PR] [Docs] TFLite tests requiring Python 3.10 and specific package versions to avoid core dumps [tvm]
via GitHub
-
[PR] [TIRX] Bind parallel loops to GPU threads before VerifyMemory [tvm]
via GitHub
-
[PR] [BugFix][TVMScript] Fix invalid f-string format spec causing TypeError on Python 3.14 [tvm]
via GitHub
-
[GH] (tvm/feat): Workflow run "CI" is working again!
GitBox
-
Re: [I] [Bug] inconsistent results for the CPU and CUDA targets. [tvm]
via GitHub
-
Re: [I] [Bug] [FRONTEND][ONNX] The onnx frontend incorrectly recognized two arguments for BitwiseNot operator that only has one arguement [tvm]
via GitHub
-
[PR] [Relax][ONNX] Support ConcatFromSequenc/SequenceInsert with new_axis=1 [tvm]
via GitHub
-
[GH] (tvm/doc161): Workflow run "CI" is working again!
GitBox
-
[PR] [Relax][ONNX] Support ConcatFromSequence new_axis=1 and refactor sequ… [tvm]
via GitHub
-
[GH] (tvm/junrus/2025-04-02/always-use-bundled-tvm-ffi): Workflow run "CI" failed!
GitBox
-
[PR] [do not merge] tvmscript printer v2 [tvm]
via GitHub
-
[PR] [Docs] Add Dataflow Pattern Language (DPL) documentation for Relax [tvm]
via GitHub
-
[PR] [Docs] Add Disco distributed runtime architecture overview [tvm]
via GitHub
-
[PR] [Docs] Add MetaSchedule advanced auto-tuning tutorial [tvm]
via GitHub
-
[PR] [Docs] Add DLight GPU scheduling tutorial [tvm]
via GitHub
-
[PR] [Docs] Add tutorial for importing models from PyTorch, ONNX, and TFLite [tvm]
via GitHub
-
[PR] [Docs] Add tvm.s_tir.analysis API reference page [tvm]
via GitHub
-
[PR] [BugFix][TVMScript] Add `doc.keyword` handling for `ExprEvaluator._visit` [tvm]
via GitHub
-
[PR] [Docs] Fix outdated paths, links, and add missing API references across documentation(3) [tvm]
via GitHub
-
[PR] [Docs] Add Relax VM architecture overview in documentation [tvm]
via GitHub
-
[PR] [Relax][TFLite] Add NON_MAX_SUPPRESSION_V5 support [tvm]
via GitHub
-
[I] [Docs] Documentation Issue (Frontend Related) [tvm]
via GitHub
-
[I] [Bug][TFLite][Relax] relax/test_frontend_tflite.py fails with AttributeError: type object 'Model' has no attribute 'Model' [tvm]
via GitHub
-
[PR] fix: TFLite model retrieval with error handling [tvm]
via GitHub