commits  

Messages by Thread

• (tvm) tag v0.25.0.post1 created (now b3e249b7d7) ruihangl
• (tvm) branch v0.25.0 updated: [CI] Build CUDA sidecar on plain manylinux, install CUDA manually (#19882) tqchen
• (tvm) branch main updated: [Relax][Frontend][TFLite] Support static hashtable find (#19879) tlopex
• (tvm) branch nightly updated (9808108e48 -> 730459c4ce) github-bot
• (tvm) branch main updated: [Relax][Frontend][TFLite] Support dynamic RANGE scalar bounds (#19867) tlopex
• (tvm) branch main updated: [DOCS] Align footer dropdown menu (#19876) tqchen
• (tvm) branch main updated: [CI] Stop building ci_lint Docker image (#19872) tlopex
• (tvm) branch main updated (1bb5cf6102 -> 15f62fe020) bohan
• (tvm-ffi) branch main updated: [PY] Support pickling FFI String and Bytes (#643) tqchen
• (tvm) branch main updated: [Relax][TFLite] Add remaining operator tests and reverse_sequence op (#19814) tlopex
• (tvm) branch main updated: [Docs] Right-align documentation footer (#19868) tqchen
• (tvm) branch main updated: [Relax] Update dropout call_tir out_ty spelling (#19874) tqchen
• (tvm-ffi) branch main updated: [PY] Distinguish FFI input and output annotations (#621) tqchen
• (tvm) branch tvm-remove-check-pr-ci-stage deleted (was 5f8c3acbae) tqchen
• (tvm) branch cleanup-testing-plugin-unused deleted (was e3cae8a873) tqchen
• (tvm) branch tvm-splithostdevice-staged-pass-consolidation deleted (was 5d42bd6859) tqchen
• (tvm) branch tvm-direct-tvm-ffi-structural-apis deleted (was b43dc89827) tqchen
• (tvm) branch revert-19842-fix/conv-transpose-dilation-legalize deleted (was 660a337c6b) tqchen
• (tvm) branch revert-19842-fix/conv-transpose-dilation-legalize created (now 660a337c6b) tqchen
  • (tvm) 01/01: Revert "[Relax] Legalize dilated conv_transpose (#19842)" tqchen
• (tvm) branch nightly updated (a9ce41e5a2 -> 9808108e48) github-bot
• (tvm) branch main updated: [Relax] Legalize dilated conv_transpose (#19842) tlopex
• (tvm-site) branch asf-site updated: Build at Tue Jun 23 02:48:29 UTC 2026 github-bot
• (tvm-site) branch main updated: Fix docs vendor ignore rule (#68) tlopex
• (tvm-site) branch mine/site/include-fontawesome-assets deleted (was 66a74944dac) tlopex
• (tvm-site) branch mine/site/include-fontawesome-assets created (now 66a74944dac) tlopex
  • (tvm-site) 01/01: Fix FontAwesome assets in deployed docs tlopex
• (tvm) branch main updated: [Docs][CI] Switch docs theme and bump images to 20260619-214849-4174cdf5 (#19828) tqchen
• (tvm) branch main updated: [Relax] Legalize nn.dropout as inference no-op (#19841) tlopex
• (tvm-site) branch asf-site updated: Build at Mon Jun 22 18:53:55 UTC 2026 github-bot
• (tvm-site) branch main updated: Recolor dense GEMM charts so DeepGEMM cuBLASLt and bf16 bars are distinguishable (#67) bohan
• (tvm-site) branch asf-site updated: Build at Mon Jun 22 15:31:09 UTC 2026 github-bot
• (tvm-site) branch main updated: Replace the opening figure in the TIRx post (#66) bohan
• (tvm) branch main updated: [REFACTOR][RELAX] Phase out Relax PrimType (#19858) tqchen
• (tvm-site) branch asf-site updated: Build at Mon Jun 22 14:42:39 UTC 2026 github-bot
• (tvm-site) branch main updated: Update TIRx post acknowledgements and contributing wording (#65) tqchen
• (tvm) branch fix/onnx-affinegrid-3d updated (35eddd90e4 -> 3a59dde7b7) guanmingchiu
• (tvm) branch fix/onnx-affinegrid-align-corners deleted (was c342721dea) guanmingchiu
• (tvm) branch fix/onnx-affinegrid-3d updated (4957ad73d8 -> 35eddd90e4) guanmingchiu
• (tvm) branch main updated: [Relax][ONNX] Support align_corners in AffineGrid op (#19864) cbalint13
• (tvm) branch fix/onnx-affinegrid-align-corners updated (5cb3fe1bb1 -> c342721dea) guanmingchiu
• (tvm) branch fix/onnx-affinegrid-3d updated (8f704ef160 -> 4957ad73d8) guanmingchiu
• (tvm) branch nightly updated (093d785e22 -> a9ce41e5a2) github-bot
• (tvm) branch fix/onnx-affinegrid-align-corners created (now 5cb3fe1bb1) guanmingchiu
  • (tvm) 01/01: [Relax][ONNX] Support align_corners in AffineGrid op guanmingchiu
• (tvm) branch fix/onnx-affinegrid-3d created (now 8f704ef160) guanmingchiu
  • (tvm) 01/01: [Relax][ONNX] Support 3D AffineGrid guanmingchiu
• (tvm-site) branch asf-site updated: Build at Mon Jun 22 04:06:54 UTC 2026 github-bot
• (tvm-site) branch main updated: Render blog math with MathJax 3 (SVG) via a no-query URL so the build self-hosts it under the CSP (#64) bohan
• (tvm-site) branch asf-site updated: Build at Mon Jun 22 04:01:40 UTC 2026 github-bot
• (tvm-site) branch main updated: Blog: add pip install command under the PyPI wheel link (#63) bohan
• (tvm-site) branch asf-site updated: Build at Mon Jun 22 03:55:58 UTC 2026 github-bot
• (tvm-site) branch main updated: Blog: link to the interactive layout demo instead of embedding it (CSP blocks cross-origin framing) (#62) bohan
• (tvm-site) branch asf-site updated: Build at Mon Jun 22 03:50:47 UTC 2026 github-bot
• (tvm-site) branch main updated: Self-host TIRx layout demo so the embedded iframe loads under the site CSP (#61) bohan
• (tvm-site) branch main updated: Load layout-demo iframe and MathJax at runtime so the site build's embed localizer doesn't reject their query URLs (#60) bohan
• (tvm-site) branch main updated: Add TIRx release blog post (#59) bohan
• (tvm) branch main updated: [Relax][Frontend][TFLite] Add explicit operator marker handling (#19824) tlopex
• (tvm) branch main updated: [Metal] Enable Metal 4 shader compilation (#19595) tlopex
• (tvm-ffi) branch main updated: [FFI] Add ref-qualified strict ObjectRef casts (#639) tqchen
• (tvm-ffi) branch main updated: [API] Add type index query mode (#640) tqchen
• (tvm) branch nightly updated (59af03c718 -> 093d785e22) github-bot
• (tvm) branch main updated: [Relax][PyTorch] Add atan2 converter (#19850) tlopex
• (tvm-ffi) branch codex/tvm-ffi-as-inline-predict-false created (now 46d2c1b2) tqchen
  • (tvm-ffi) 01/01: tvm-ffi: streamline as and object downcast paths tqchen
• (tvm) branch main updated: [Relax][ONNX] Accept 1-D scalar inputs in NonMaxSuppression (#19843) cbalint13
• (tvm) branch nightly updated (7bd73e5ad2 -> 59af03c718) github-bot
• (tvm-ffi) branch main updated: [CORE] Invert object/type_traits dependency layering (#638) tqchen
• (tvm) branch main updated: [Relax][ONNX] Drop NaN-preservation isnan-where wrappers (#19847) tqchen
• (tvm) branch main updated: [Tests] Clean unused tvm.testing helpers (#19846) tqchen
• (tvm) branch main updated: [Docker] Bump CI image deps: sphinx-book-theme + z3-static (#19835) tqchen
• (tvm) branch cleanup-testing-plugin-unused created (now e3cae8a873) tlopex
  • (tvm) 01/01: Clean unused tvm.testing helpers tlopex
• (tvm) branch main updated: [BUILD] Sync fallback version strings to 0.26 dev cycle (#19845) tqchen
• (tvm) tag v0.25.0 created (now c7ba0735a4) ruihangl
• svn commit: r85340 - release/tvm/tvm-v0.25.0 ruihangl
• (tvm) branch main updated: [TIRx] Phase out flat device-intrinsic op aliases (#19838) bohan
• (tvm) branch main updated: [Relax] Fix matmul and reductions with zero-size dimension return uninitialized memory (#19680) guanmingchiu
• (tvm) branch main updated: [Relax][ONNX] Preserve NaN in Relu to align with ONNX Runtime (#19750) guanmingchiu
• (tvm) branch main updated: [CPP_RPC] Replace legacy OS-specific API with std:: libraries (#19840) tqchen
• (tvm) branch main updated: [BUILD] Bump tvm-ffi after RuntimeTypeIndex optimization (#19834) tqchen
• (tvm) branch main updated: [Arith] Add Analyzer::Clone for deep-copying analyzer state (#19836) tqchen
• (tvm) branch main updated: [Docs]Rework Bring Your Own Codegen tutorial and add TensorRT example (#19839) tqchen
• (tvm) branch main updated: [Web] Avoid redundant OPFS lookup on cache hit (#19791) guanmingchiu
• (tvm) branch nightly updated (0bc3a6fa5f -> 7bd73e5ad2) github-bot
• (tvm-ffi) branch main updated: [OBJECT] Make object info macro compatible with CRTP (#636) tqchen
• (tvm) branch main updated: [Arith] Restrict floormod coefficient reduction to keep DetectIterMapstable (#19832) tlopex
• (tvm) branch main updated: [Tests] Remove dead helpers and unused probes from tvm.testing (#19821) tqchen
• (tvm-ffi) branch main updated: [OBJECT] Optimize dynamic RuntimeTypeIndex loads (#634) tqchen
• (tvm-ffi) branch main updated: [CI] Ignore existing DLLs in Windows wheel repair (#635) tqchen
• (tvm) branch main updated: fix: Support 5D volumetric inputs in ONNX GridSample frontend converter (#19816) tlopex
• (tvm) branch main updated: [Arith] Let IRMutatorWithAnalyzer take a const Analyzer& (#19829) tlopex
• (tvm) branch main updated: [Relax][TensorRT] Add partition_for_tensorrt and a pattern table (#19820) ruihangl
• (tvm-ffi) branch main updated: [CI] Phase out Python 3.8 wheel builds (#633) tqchen
• (tvm) branch main updated: [FFI][ABI] Bump tvm-ffi to latest (#19831) ruihangl
• (tvm-ffi) branch main updated: [CI] Update Jimver/cuda-toolkit to allowed ref v0.2.35 (#631) tqchen
• (tvm-ffi) branch main updated: [FIX] Avoid -Wassume error in structural visit VisitImpl (#632) tqchen
• (tvm) branch nightly updated (ddfec9c3d6 -> 0bc3a6fa5f) github-bot
• (tvm) branch main updated: [Relax][Frontend][TFLite] Add missing TFLite operator mappings (#19813) tlopex
• (tvm) branch main updated: [ARITH] Add optional Z3-backed proving to Analyzer (#19667) tlopex
• (tvm) branch main updated: [Relax][Frontend][NN] Fix SourceModule include resolution for installed wheels (#19822) tqchen
• (tvm) branch main updated: [Tests] Inline thin gating helpers in the pytest plugin and tvm.testing.env (#19819) tlopex
• (tvm) branch main updated: [CI] Drop redundant conda LLVM install in GH Actions build (#19823) tlopex
• (tvm) branch main updated: Preserve ONNX BatchNormalization inference mode (#19818) tlopex
• (tvm) branch main updated: [BUILD] Hide static linked library symbols in shared libs (#19817) bohan
• (tvm) branch main updated: [Relax][Frontend][TFLite] Add RFFT2D op and supporting TIR kernels (#19812) tlopex
• (tvm-ffi) branch main updated: Avoid unused type_index local in structural visit (#629) tqchen
• (tvm-ffi) branch main updated: [CMake] Format static symbol helper condition (#628) tqchen
• (tvm-ffi) branch main updated: [BUILD] Hide symbols from linked static libraries (#627) tqchen
• (tvm-ffi) branch main updated: [CI] Bump pinned GitHub Action hashes (#626) tqchen
• (tvm-ffi) branch main updated: [DOCS] Clarify CStrParts error handling usage (#625) tqchen
• (tvm-site) branch main updated: [CI] Update setup-uv ref for TVM-FFI docs publish (#58) tqchen
• (tvm-site) branch tvm-site-update-setup-uv-ref-for-tvm-ffi-docs-publish created (now 64e7525e6fb) tqchen
  • (tvm-site) 01/01: [CI] Update setup-uv ref for TVM-FFI docs publish tqchen
• (tvm) branch main updated: [FIX][TIRX] Fix dangling Op static reference warning (#19806) bohan
• (tvm) branch main updated: [Relax][TensorRT] Update BYOC operator converters from Relay to Relax (#19810) tqchen
• (tvm) branch main updated: [Tests] Drop tautological env-probe implication tests (#19811) tqchen
• (tvm-ffi) branch main updated: [CI] Update astral-sh/setup-uv to allowed ref v8.2.0 (#624) yaxingcai
• (tvm) branch nightly updated (e4da848e57 -> ddfec9c3d6) github-bot
• svn commit: r85270 - dev/tvm/tvm-v0.25.0-rc1 ruihangl
• (tvm) tag v0.25.0.rc1 updated (a28a8728a7 -> c7ba0735a4) ruihangl
• (tvm) branch main updated: [Tests] Remove the now-unused tvm.testing.parameters() helper (#19807) tlopex
• (tvm) branch v0.25.0 updated (a28a8728a7 -> c7ba0735a4) ruihangl
• svn commit: r85265 - dev/tvm/tvm-v0.25.0-rc1 ruihangl
• (tvm) tag v0.25.0.rc1 updated (0815e00052 -> a28a8728a7) ruihangl
• (tvm) branch v0.25.0 updated (0815e00052 -> a28a8728a7) ruihangl
• (tvm) branch main updated: [Tests] Migrate tvm.testing.parameters() to pytest.mark.parametrize (#19803) tqchen
• (tvm) branch main updated: [Relax] Fix FuseOpsByPattern dropping bound constants on duplicate-structure functions (#19801) tqchen
• svn commit: r85264 - dev/tvm/tvm-v0.25.0-rc1 ruihangl
• (tvm) tag v0.25.0.rc1 created (now 0815e00052) ruihangl
• (tvm) branch v0.25.0 updated (a9a9fc57ba -> 0815e00052) ruihangl
• (tvm) branch main updated: [Tests][Refactor] Remove unused testing helpers (#19800) tlopex
• (tvm) branch main updated (b046e69a7f -> 9d6e1cf07f) tlopex
• (tvm) branch main updated: [CI] Remove Jenkins PR linter step (#19798) tqchen
• (tvm-site) branch asf-site updated: Build at Tue Jun 16 17:18:23 UTC 2026 github-bot
• (tvm-site) branch main updated: Set up default protection ruleset for default and release branches (#56) tqchen
• (tvm) branch main updated: [REFACTOR][IR] Simplify CallingConv attribute access (#19799) ruihangl
• (tvm) branch tvm-remove-check-pr-ci-stage updated (7cba56e9fd -> 5f8c3acbae) tqchen
• (tvm-ffi) branch main updated (8a0b93f -> 807b17a) junrushao
• (tvm) branch main updated: [Web] use singular requestFileHandle() instead of requestFileHandles() (#19780) guanmingchiu
• (tvm) branch main updated: [CI] Pin GitHub Actions to SHA for ASF INFRA compliance (#19793) guanmingchiu
• (tvm) branch main updated: [REFACTOR] Phase out unused queue and rang license entries (#19794) ruihangl
• (tvm) branch main updated: [Web] Destroy GPUDevice once on buffer creation error (#19790) guanmingchiu
• (tvm) branch tvm-remove-check-pr-ci-stage created (now 7cba56e9fd) tqchen
• (tvm) branch main updated: [Docs] Modernize test-gating documentation (#19788) guanmingchiu
• (tvm) branch main updated: [TIRx][RISC-V] Use scalable RVV loops for fixed vectorize (#19776) cbalint13
• (tvm) branch main updated: [Tests] Replace remaining requires_* helpers with standard pytest (#19787) tqchen
• (tvm) branch main updated: [Tests] Make TargetCreation.DeduplicateKeys host-agnostic on AArch64 (#19786) tqchen
• (tvm) branch main updated: [Relax][TensorRT] Update TensorRT runtime to 10 (#19789) tqchen
• (tvm) branch main updated: [TIRX][CUDA] Framework support for FA4, CLC intrinsics, and nvfp4 tcgen05 GEMM (#19785) tqchen
• (tvm) branch nightly updated (21298c77ed -> e4da848e57) github-bot
• (tvm) branch main updated: [AGENT] Migrate agent instructions to vendor-neutral layout (#19783) tqchen
• (tvm) branch main updated: [CUDA] Narrow the cuda extra from cuda-python to cuda-bindings (#19784) ruihangl
• (tvm) branch main updated: [REFACTOR][IR] Cleanup IR naming utilities (#19781) tlopex
• (tvm) branch main updated: [Docs][CI] Bump tlcpack-sphinx-addon to restore search result summaries (#19782) tqchen
• (tvm) branch main updated: [Relax][ONNX] Make ReduceMax/ReduceMin NaN propagation order-independent(numpy semantics) (#19755) tlopex
• (tvm) branch main updated: [Fix] nn.attention support dynamic batch_size (#19779) tlopex
• (tvm) branch v0.25.0 updated (daf90cbd79 -> a9a9fc57ba) ruihangl
• (tvm) branch main updated: [REFACTOR][PYTHON] Consolidate backend autoload infra (#19769) ruihangl
• (tvm) branch main updated: [REFACTOR][CUDA] Phase out cuda_common.h (#19770) tqchen
• (tvm) branch main updated: [CMAKE] Upgrade TVM build baseline to C++20 (#19734) tqchen
• (tvm) branch main updated: [CPP_RPC] Bugfix race conditions and enhance print infos (#19778) tqchen
• (tvm) branch v0.25.0 updated: [CI] Merge PR against its target branch instead of main (#19712) (#19775) tqchen
• (tvm) branch nightly updated (d291513131 -> 21298c77ed) github-bot
• (tvm) branch main updated: [Relax][ONNX] Support exclusive option in CumSum (#19773) tlopex
• (tvm) branch main updated (4119c9fecd -> 44b55a05fb) tlopex
• (tvm) branch main updated: [REFACTOR][CUDA] Phase out l2 cache flush preproc test (#19768) tlopex
• (tvm) branch main updated: [MetaScheduler] Improve print info about builder/runner state (#19767) tqchen
• (tvm) branch main updated (e43555f739 -> 8b79dfdb80) bohan
• (tvm) branch main updated: [REFACTOR][DataType] Phase out target custom datatype support (#19760) tqchen
• (tvm) branch main updated: [CI] Drop redundant cmake/ninja install from the Linux wheel CUDA sidecar (#19761) tqchen
• (tvm) branch main updated: [Runtime][CoreML] Fix FFI casts in CoreML runtime (#19762) tqchen
• (tvm) branch nightly updated (6f9609f10a -> d291513131) github-bot
• (tvm) branch main updated: [REFACTOR][VM] Move CUDA graph VM builtin back under VM runtime (#19758) tlopex
• (tvm-ffi) branch main updated: Adopt AGENTS.md for agent guidance (#620) ruihangl
• (tvm) branch main updated: [Relax][PyTorch] Add logical_or and logical_xor converters (#19756) tlopex
• (tvm) branch main updated: [Tests][AArch64] Make SVE codegen assertions robust across LLVM versions (#19752) tqchen
• (tvm) branch main updated: [S-TIR][CUDA] Fix legacy predicated cp.async zero fill (#19741) tqchen
• (tvm) branch main updated: [TIRX][Tests] Fix LLVM version gate for vectorized lround (#19753) tqchen
• (tvm) branch main updated: [CI] Updated cibw to 4.1.0 (#19754) tqchen
• (tvm) branch nightly updated (2a16d98b9e -> 6f9609f10a) github-bot
• (tvm) branch main updated: [CI] Run s_tir/transform tests in the python-unittest stage (#19737) tlopex
• (tvm) branch main updated: [S-TIR][Tests] Mark test_cp_async_in_if_then_else as xfail (#19751) bohan
• (tvm-ffi) branch main updated: [REFACTOR][STUBGEN] refactor the stubgen logic. (#608) tqchen
• (tvm) branch main updated: [Tests][LLVM] Gate stepvector intrinsic rename on LLVM 20 (#19745) tqchen
• (tvm) branch main updated: [Runtime][Tests] Drop int4 from random_fill test, fix dtype error message (#19748) tqchen
• (tvm) branch main updated: [Runtime][Disco] Fix session attribute storage, NVSHMEM build, and test gating (#19736) tqchen
• (tvm) branch main updated: [Codegen][LLVM][Tests] Gate +v9a vscale_range expectation on LLVM version (#19744) tqchen
• (tvm) branch main updated: [CI] Align cuda-python with PyTorch cuda-bindings (#19738) tqchen
• (tvm) branch main updated: [Hexagon][Tests] Clean up stale hexagon tests (#19747) tqchen
• (tvm) branch main updated: [Tests] Fix flaky popen pool executor test (#19746) tqchen
• (tvm) branch nightly updated (a4a2bf5b89 -> 2a16d98b9e) github-bot
• (tvm) branch main updated: [S-TIR] Fix software pipeline offsets for legacy MMA intrinsics (#19742) tlopex
• (tvm) branch main updated: [Tests] Check WebGPU volatile allreduce annotation structurally (#19740) tlopex
• (tvm) branch main updated: [TIRx] Use canonical PTX async script API in s_tir test (#19739) tlopex
• (tvm) branch investigate-s-tir-nested-pipeline-mma updated (3705f396e4 -> e56ca66dcd) tlopex
• (tvm) branch investigate-s-tir-nested-pipeline-mma updated (adbd870e8f -> 3705f396e4) tlopex
• (tvm) branch investigate-s-tir-nested-pipeline-mma updated (f180256f0a -> adbd870e8f) tlopex
• (tvm) branch investigate-s-tir-nested-pipeline-mma created (now f180256f0a) tlopex
  • (tvm) 01/01: Fix software pipeline legacy MMA offsets tlopex

• Earlier messages