commits

Messages by Date

2026/05/28 (tvm) 03/22: feat(op-dispatch): add warp ldmatrix/stmatrix dispatch for Tx.copy (#630) bohan
2026/05/28 (tvm) 16/22: feat(tirx): add M=128 dispatch + layout for .16x*b tcgen05.ld/st (#646) bohan
2026/05/28 (tvm) 21/22: fix(arith): memoize IntervalSet variable relaxation to avoid exponential blowup (#652) bohan
2026/05/28 (tvm) 18/22: feat(gemm_async): accept Layout F C operand for M=64 MMAs (#648) bohan
2026/05/28 (tvm) 04/22: refactor(op-dispatch): rename copy/warp_matrix.py to copy/ld_stmatrix.py (#631) bohan
2026/05/28 (tvm) branch tir-bench created (now cd8790bc54) bohan
2026/05/28 (tvm) 07/22: feat(tvmscript): add @Tx.jit decorator, Tx.constexpr params, Tx.wg_reg_tile (#635) bohan
2026/05/28 (tvm) 22/22: feat(infra): util-gated GPU selection for tir-bench + per-config warmup/repeat bohan
2026/05/28 (tvm) branch main updated: [REFACTOR][ARITH] Phase out arith/scalable_expression; arith no longer proves over scalable vectors (#19638) tlopex
2026/05/28 (tvm-ffi) branch main updated: [CI] Use uv tool run for sdist build instead of pipx (#600) yongwww
2026/05/28 (tvm) branch main updated: [REFACTOR][SCRIPT] tvmscript streamline: lift printer.h, restore one-way dep, migrate dialect config to extra_config (#19631) tlopex
2026/05/28 (tvm-ffi) branch main updated: [FEAT] Streamline AccessPath/AccessStep print format (#598) tqchen
2026/05/28 (tvm-ffi) branch main updated: [FEAT] Optimize Expected<T> for minimal compiled code and efficiency (#599) tqchen
2026/05/28 (tvm) branch main updated: [CI] Remove tvm-lint from tvm-bot (#19629) tqchen
2026/05/27 (tvm) branch nightly updated (dcbebe7bfd -> 61ae85b9d1) github-bot
2026/05/27 (tvm) branch main updated: [REFACTOR][PYTHON] Consolidate derived_object into tvm.ir.utils (#19630) tlopex
2026/05/27 (tvm) branch main updated: [REFACTOR][RUNTIME] Structural reorganization: locality moves for thread_map, texture, minrpc, disco, contrib (#19628) tlopex
2026/05/27 (tvm) branch main updated: [BugFix][Vulkan][CodeGen] Change OpControlBarrier to AcquireRelease (#19619) tqchen
2026/05/27 (tvm) branch main updated: [REFACTOR][IR][FFI] Bump tvm-ffi (+ SEqHashDef migration) and phase out tvm/ir/repr.h (#19627) bohan
2026/05/27 (tvm) branch main updated: [REFACTOR][IR] Inline ReplaceGlobalVars into AttachGlobalSymbol (#19625) tlopex
2026/05/27 (tvm) branch main updated: [REFACTOR][PYTHON] Lift compiler/CLI/process modules from tvm.contrib to tvm.support (#19624) bohan
2026/05/27 (tvm) branch main updated: [REFACTOR][RUNTIME] Relocate nvtx.h to tvm/support/cuda and make it header-only (#19621) bohan
2026/05/27 (tvm) branch main updated: [REFACTOR][RUNTIME] Remove leftover microTVM/CRT crumbs (#19622) bohan
2026/05/27 (tvm) branch main updated: [REFACTOR][RUNTIME] Phase out tvm::runtime::regex_match (#19620) bohan
2026/05/27 (tvm-ffi) branch main updated: [FEAT][FFI] Add ostream operator<< for Any/ObjectRef/Variant/Optional (#596) tqchen
2026/05/27 (tvm) branch main updated: [IR] Rename Call annotations to attrs (#19618) tqchen
2026/05/26 (tvm) branch nightly updated (4dad956cba -> dcbebe7bfd) github-bot
2026/05/26 (tvm-site) branch asf-site updated: Build at Wed May 27 05:52:08 UTC 2026 github-bot
2026/05/26 (tvm-site) branch main updated: Update download.md for v0.24.0 (#57) ysh329
2026/05/26 (tvm-site) branch asf-site updated: deploying docs (apache/tvm@fa66213249a361656fea055d80291cf0e6b2ff1a) tqchen
2026/05/26 (tvm) branch main updated: [Relax][Frontend][TFLite] Add UNIDIRECTIONAL_SEQUENCE_RNN converter (#19601) tlopex
2026/05/26 (tvm) branch main updated: [Relax][Frontend][TFLite] Support control-flow multi-subgraph operators (#19616) tlopex
2026/05/26 (tvm) branch main updated: [REFACTOR][TIR] Tie AnnotateDeviceRegions/SplitHostDevice/LowerDeviceKernelLaunch together (#19605) tlopex
2026/05/26 (tvm) branch main updated: [REFACTOR][IR] attrs.h follow-up cleanup: drop legacy vtable / rename / phase out AttrFieldInfo (#19615) tlopex
2026/05/26 (tvm) branch main updated: [CMAKE][RUNTIME] Link tvm_rpc with all backend runtime libraries (#19617) tlopex
2026/05/26 (tvm) branch main updated: [REFACTOR][IR] Inline ApplyPassToFunction into relax decompose_ops, delete the util (#19612) tlopex
2026/05/26 (tvm) branch main updated: [REFACTOR][IR] Phase out src/ir/structural_{hash,equal}.cc to tvm-ffi (#19613) tlopex
2026/05/26 (tvm-site) branch asf-site updated: deploying docs (apache/tvm@58d6a5a8f972002ba17f387d961c867a418d987e) tqchen
2026/05/26 (tvm) branch main updated: [REFACTOR] Move src/ir/script_printer.cc to src/script/printer/ (#19611) tlopex
2026/05/26 (tvm) branch main updated: [Docs] Reorganize development guide content (#19606) tlopex
2026/05/26 (tvm-site) branch asf-site updated: deploying docs (apache/tvm@b1e1566f8264240a5e5a8cae836a212e9b43687f) tqchen
2026/05/26 (tvm) branch main updated: [REFACTOR][IR] Cleanup attrs.h: drop NullValue, AttrsNodeReflAdapter, legacy BaseAttrsNode methods (#19607) tqchen
2026/05/25 (tvm) branch nightly updated (cae6cb89b7 -> 4dad956cba) github-bot
2026/05/25 (tvm) branch main updated: Fix PytestUnknownMarkWarning: Unknown pytest.mark.adreno_clml (#19602) tlopex
2026/05/25 (tvm) branch main updated: [Relax][Frontend][TFLite] Support quantized TFLite import via QDQ decomposition (#19538) tlopex
2026/05/25 (tvm) branch main updated: [REFACTOR][RELAX] Fold CalleeCollector into relax DeadCodeElimination (#19603) tlopex
2026/05/24 (tvm) branch nightly updated (a7463e9b2d -> cae6cb89b7) github-bot
2026/05/24 (tvm) branch main updated: [IR] Add annotations to Call nodes (#19597) bohan
2026/05/24 (tvm) branch main updated: [CodeGen][CUDA] Move fast math intrinsic lowering option to PassContext (#19596) tlopex
2026/05/23 (tvm) branch nightly updated (4052880e7c -> a7463e9b2d) github-bot
2026/05/23 (tvm) branch main updated: [RPC][Tracker] Bound msg_size to MAX_TRACKER_MSG_BYTES to prevent unbounded buffer growth (#19586) tlopex
2026/05/23 (tvm) branch main updated: [Relax] Normalize negative concat axis in ReorderPermuteDimsAfterConcat (#19588) tlopex
2026/05/22 (tvm) branch nightly updated (a1e4cd82fe -> 4052880e7c) github-bot
2026/05/22 (tvm) branch runtime-modularize updated (f659c83a4d -> e145b16ea6) tqchen
2026/05/21 (tvm) branch runtime-modularize updated (3079d95eb6 -> f659c83a4d) tqchen
2026/05/21 (tvm) branch runtime-modularize updated (3e89882615 -> 3079d95eb6) tqchen
2026/05/21 (tvm) branch runtime-modularize created (now 3e89882615) tqchen
2026/05/21 (tvm-ffi) branch main updated: [EXTRA][FEAT] VisitErrorContext for visit-context-aware error reporting (#587) tqchen
2026/05/20 (tvm) branch nightly updated (1720d305ae -> a1e4cd82fe) github-bot
2026/05/20 (tvm) branch main updated: [Relay/ONNX] Add RMSNormalization converter for ONNX opset 23 (#19590) tlopex
2026/05/20 (tvm) branch main updated: [Relax][Frontend][TFLite] Support StableHLO region-based ops and multi-subgraph models (#19587) tlopex
2026/05/19 (tvm) branch nightly updated (13ce30b988 -> 1720d305ae) github-bot
2026/05/19 (tvm) branch main updated: [Relax][ONNX] Fix TopK scalar K extraction in from_onnx (#19573) tlopex
2026/05/19 (tvm) branch nightly updated (bc1a904ec1 -> 13ce30b988) github-bot
2026/05/18 (tvm) branch main updated: [BugFix][Target][LLVM] Route sinh/cosh/atan/asinh/erf through libm extern (#19568) tlopex
2026/05/18 (tvm) branch main updated: [TVMScript] Handle undefined functions when dumping IRModule (#19583) tlopex
2026/05/18 (tvm) branch main updated: [RFC][CodeGen][CUDA]: Gate fast math intrinsic lowering behind target option (#19565) tlopex
2026/05/18 (tvm) branch main updated: [BugFix][Target][LLVM] Use libm for asin/acos instead of buggy inline Taylor (#19567) tlopex
2026/05/17 (tvm) branch nightly updated (4b93f2060f -> bc1a904ec1) github-bot
2026/05/17 (tvm) branch main updated: [Relax][ONNX] Prevent `Div` divide-by-zero crashes (#19566) mshr
2026/05/15 (tvm-ffi) branch main updated: [FIX][RUST] use `$crate::` in tvm_ffi_dll_export_typed_func! and ensure! (#590) tqchen
2026/05/14 (tvm) branch nightly updated (b473185418 -> 4b93f2060f) github-bot
2026/05/14 (tvm) branch main updated: [Fix][Relax] Lower bool prod as logical all (#19557) tlopex
2026/05/14 svn commit: r84525 - release/tvm/tvm-v0.24.0 ysh329
2026/05/14 svn commit: r84524 - release/tvm/tvm-v0.24.0 ysh329
2026/05/14 svn commit: r84523 - release/tvm/tvm-v0.24.0 ysh329
2026/05/14 svn commit: r84522 - dev/tvm/tvm-v0.24.0-rc0 release/tvm/tvm-v0.24.0 ysh329
2026/05/13 (tvm) branch nightly updated (bedfcb2b85 -> b473185418) github-bot
2026/05/13 (tvm) tag v0.24.0 created (now af3e4ba814) ysh329
2026/05/13 (tvm-ffi) branch main updated: [BUILD] TVM_FFI_COLD_CODE / TVM_FFI_PREDICT_FALSE macros and cold-marking of error paths (#589) tqchen
2026/05/13 (tvm-ffi) branch main updated: [Minor] log ninja result (#584) tqchen
2026/05/13 (tvm-ffi) branch main updated: [BugFix][ROCm] Prefer upstream PyTorch DLPack API in torch extension loader (#585) tqchen
2026/05/13 (tvm) branch main updated: [Relax][ONNX] Add ONNX Backend Tests for systematic frontend coverage (#19515) mshr
2026/05/12 (tvm) branch nightly updated (378c4f3043 -> bedfcb2b85) github-bot
2026/05/12 (tvm) branch main updated: [Relax][ONNX] Set `max_output_boxes_per_class` default value to 0 for NonMaxSuppression (#19547) tlopex
2026/05/12 (tvm) branch main updated: [Fix][Relax]: ONNX Clip NaN bounds and preserve input NaN (ORT parity) (#19535) tlopex
2026/05/11 (tvm) branch nightly updated (6b27d19497 -> 378c4f3043) github-bot
2026/05/11 (tvm) branch main updated: [BugFix][Relax]: handle ONNX ScatterElements reduction (#19527) tlopex
2026/05/11 (tvm) branch main updated: [Contrib] Fix CUDA contrib build after FFI/header cleanups (#19539) tlopex
2026/05/11 (tvm) branch dependabot/pip/docker/python/urllib3-2.6.3 deleted (was b543a93d4c) github-bot
2026/05/11 (tvm) branch dependabot/pip/docker/python/urllib3-2.7.0 created (now 91a2e5b297) github-bot
2026/05/11 (tvm-ffi) branch main updated: [FEAT] Split SEqHashDef into recursive and non-recursive variants (#583) tqchen
2026/05/11 (tvm) branch main updated: [Relax][Frontend][TFLite] Add initial StableHLO builtin operator support (#19536) tlopex
2026/05/11 (tvm) branch main updated: [TIR] Add cooperative_tensor builtins and metal.cooperative_tensor storage scope (#19423) tlopex
2026/05/11 (tvm) branch main updated: [Relax][Frontend] Add TFLite Frontend Support for CONV_3D_TRANSPOSE (#19530) tlopex
2026/05/11 (tvm) branch main updated: [Relax][ONNX] Normalize negative indices before the take call for `Gather` operator (#19525) tlopex
2026/05/10 (tvm-ffi) branch main updated: [FEAT][REFLECTION] Add tvm::ffi::reflection::overload_cast to pick overloaded function (#582) junrushao
2026/05/10 (tvm-ffi) branch overload-cast-helper created (now 056b62b) tqchen
2026/05/10 (tvm-ffi) branch overload-cast-helper deleted (was 056b62b) tqchen
2026/05/10 (tvm-ffi) 01/01: [FEAT] Add tvm::ffi::reflection::overload_cast helper tqchen
2026/05/10 (tvm-ffi) branch handle-rawstr-bytearrayptr-callback deleted (was 789161f) tqchen
2026/05/10 (tvm-ffi) branch seqhashdef-non-recursive deleted (was 107ad51) tqchen
2026/05/09 (tvm) branch nightly updated (4ab312bf12 -> 6b27d19497) github-bot
2026/05/09 (tvm-ffi) 01/01: [FEAT] Split SEqHashDef into recursive and non-recursive variants tqchen
2026/05/09 (tvm-ffi) branch seqhashdef-non-recursive created (now 107ad51) tqchen
2026/05/09 (tvm) branch main updated: [REFACTOR][IR] Remove dead AttrFunctor template (#19528) tlopex
2026/05/08 (tvm) branch nightly updated (446bd2dbf0 -> 4ab312bf12) github-bot
2026/05/08 (tvm) branch main updated: [Relax][Frontend][TFLite] Add Conv3D support (#19523) tlopex
2026/05/08 svn commit: r84407 - dev/tvm/tvm-v0.24.0-rc0 ysh329
2026/05/08 svn commit: r84406 - dev/tvm/tvm-v0.24.0-rc0 ysh329
2026/05/08 (tvm) branch main updated: [Relax][PyTorch] Fix segfault in from_exported_program when model uses index_put_ with tuple output (#19488) tlopex
2026/05/08 (tvm) branch main updated: [Relax][TFLite] Add gather frontend expected IRModule tests (#19516) tlopex
2026/05/06 (tvm) branch nightly updated (75a48a0e2d -> 446bd2dbf0) github-bot
2026/05/06 (tvm) branch main updated: [BugFix][S-TIR] Wrap bare scalar bodies in DefaultGPUSchedule to avoid root-block crash (#19514) tlopex
2026/05/06 (tvm) tag v0.25.dev0 created (now a354b4f59e) ysh329
2026/05/06 (tvm) tag v0.24.0.rc0 created (now af3e4ba814) ysh329
2026/05/06 (tvm) branch v0.24.0 created (now af3e4ba814) ysh329
2026/05/06 (tvm) branch main updated: [BugFix][Relax][Torch] Honor `correction` in std/var converter (#19512) tlopex
2026/05/06 (tvm) branch main updated: [BugFix][Relax][Torch] Honor multi-axis dims in torch.flip converter (#19511) tlopex
2026/05/05 (tvm) branch nightly updated (82a37dac1d -> 75a48a0e2d) github-bot
2026/05/05 (tvm) branch dependabot/pip/docker/python/pip-26.0 deleted (was e9f7ed6092) github-bot
2026/05/05 (tvm) branch dependabot/pip/docker/python/pip-26.1 created (now cb59c10ab9) github-bot
2026/05/05 (tvm) branch main updated: [Web] Add support for OPFS (#19494) guanmingchiu
2026/05/05 (tvm-ffi) branch main updated: Update ML infrastructure section with XGrammar link (#581) tqchen
2026/05/05 (tvm-ffi) branch main updated: chore(release): Version bump after release v0.1.11 (#579) junrushao
2026/05/04 (tvm) branch nightly updated (87bf3022b7 -> 82a37dac1d) github-bot
2026/05/04 svn commit: r84308 - release/tvm/tvm-ffi-v0.1.11 yongwww
2026/05/04 (tvm-ffi) tag v0.1.11 created (now 3c35034) yongwww
2026/05/04 (tvm) branch main updated: [BugFix][Relax][ONNX] Resolve param Vars in Concat to handle mixed Shape/Tensor inputs (#19498) tlopex
2026/05/04 (tvm) branch main updated: [BugFix][Relax] Fix scatter_elements and scatter_nd CUDA compilation (#19497) tlopex
2026/05/03 (tvm) branch nightly updated (8873a4c8a5 -> 87bf3022b7) github-bot
2026/05/03 (tvm) branch main updated: [Relax][Frontend][TFLite] Add tests coverage for SPACE_TO_BATCH_ND and BATCH_TO_SPACE_ND (#19499) tlopex
2026/05/03 (tvm) branch main updated: [BUGFIX][TIR] Skip bool-typed expressions in CSE (#19502) tlopex
2026/05/02 (tvm) branch nightly updated (fbbbae994d -> 8873a4c8a5) github-bot
2026/05/02 (tvm) branch main updated: [Relax][Frontend][TFLite] Add segment operator mappings (#19491) tlopex
2026/05/02 (tvm) branch main updated: [Relax][Frontend] Add ParameterList and ParameterDict containers (#19495) tlopex
2026/05/02 (tvm) 01/02: [release] Update version to 0.24.0 on main branch syfeng
2026/05/02 (tvm) 02/02: [release] Update version to 0.25.dev0 on main branch syfeng
2026/05/02 (tvm) branch main updated (baec626676 -> a354b4f59e) syfeng
2026/05/02 (tvm) branch main updated: [Metal] Include logging headers for metal (#19493) tlopex
2026/05/02 (tvm) branch main updated: [BugFix][Relax] Add legalize for isnan, isinf, isfinite (#19492) tlopex
2026/05/02 (tvm) branch main updated: [Relax][Frontend][TFLite] Add BROADCAST_TO, EMBEDDING_LOOKUP, and SELECT_V2 (#19489) tlopex
2026/05/01 (tvm) branch nightly updated (d6ef18e771 -> fbbbae994d) github-bot
2026/05/01 (tvm) branch main updated: [Relax][Frontend][TFLite] Add SCATTER_ND operator for Relax TFLite (#19490) tlopex
2026/05/01 (tvm) branch main updated: [Relax][ONNX] Fix CumSum axis handling: support runtime axis tensor, error on multi-element axis (#19467) tlopex
2026/05/01 (tvm) branch main updated: [Relax][Frontend][TFLite] Add `RANDOM_UNIFORM`, `RANDOM_STANDARD_NORMAL`, and `MULTINOMIAL` (#19473) tlopex
2026/05/01 (tvm) branch main updated: [Relax][Frontend][TFLite] Add BROADCAST_ARGS operator mapping (#19487) tlopex
2026/04/30 (tvm) branch nightly updated (556571fc9d -> d6ef18e771) github-bot
2026/04/30 (tvm) branch main updated: [Relax][Frontend][TFLite] Add DILATE operator mapping (#19481) tlopex
2026/04/30 (tvm) branch main updated: [Relax][Frontend][TFLite] Add ATAN2 op and TFLite mapping (#19485) tlopex
2026/04/30 (tvm) branch main updated: [BugFix][Relax][ONNX] Fix ConstantOfShape converter when value attr is absent (#19480) tlopex
2026/04/30 (tvm-ffi) branch main updated: fix(dataclass): collect py_class fields from plain bases (#575) junrushao
2026/04/30 (tvm-ffi) branch main updated: chore(doc): Temp workaround missing pytorch docs (#577) yaxingcai
2026/04/30 svn commit: r84226 - dev/tvm/tvm-ffi-v0.1.11-rc2 yongwww
2026/04/30 svn commit: r84223 - dev/tvm/tvm-ffi-v0.1.11-rc2 yongwww
2026/04/30 (tvm) branch main updated: [FFI][ABI] Bump tvm-ffi to 0.1.11rc2 (#19484) yaxingcai
2026/04/30 (tvm) branch main updated: [REFACTOR] Delete src/support/libinfo.cc; replace with runtime FFI-registry env query (#19477) tqchen
2026/04/30 (tvm) branch main updated: [REFACTOR][SCRIPT] TVMScript dialect-friendly refactor: per-dialect restructure + dialect registry (#19479) tqchen
2026/04/29 (tvm) branch nightly updated (c1415d6e4d -> 556571fc9d) github-bot
2026/04/29 (tvm) branch main updated: [REFACTOR][S-TIR] Move tvm/support/random_engine.h → tvm/s_tir/random_engine.h (#19475) tqchen
2026/04/29 (tvm) branch main updated: [Relax][Frontend][TFLite] Fix `STRIDED_SLICE` negative stride and add `STRIDED_SLICE/SPLIT_V` tests (#19468) tlopex
2026/04/29 (tvm) branch main updated: [REFACTOR][IR] Move tvm/support/with.h → tvm/ir/with_context.h (#19474) tqchen
2026/04/29 (tvm) branch main updated: [REFACTOR][RUNTIME] Phase out IntTuple alias; use ffi::Shape directly (#19471) tlopex
2026/04/29 (tvm) branch main updated: [REFACTOR][RUNTIME] Phase out include/tvm/runtime/builtin_fp16.h (#19472) tqchen
2026/04/29 (tvm) branch main updated: [REFACTOR][RUNTIME] Phase out include/tvm/runtime/threading_backend.h (#19469) bohan
2026/04/29 (tvm) branch main updated: [S-TIR][Dlight] Add layered fall back strategy to handle missing attr `max_shared_memory_per_block` (#19453) mshr
2026/04/28 (tvm) branch main updated: [Relax][Frontend][TFLite] Add DENSIFY operator test and fix prefetched handling (#19421) tlopex
2026/04/28 (tvm) branch nightly updated (11ac2ad97c -> c1415d6e4d) github-bot
2026/04/28 (tvm) branch main updated: [Relax][Frontend][TFLite] Add NON_MAX_SUPPRESSION_V4 converter (#19464) tlopex
2026/04/28 (tvm) branch main updated: [Relax][Frontend][TFLite] Add BITCAST operator mapping (#19466) tlopex
2026/04/28 (tvm) branch main updated: [Relax][Frontend][TFLite] Fix dynamic FILL/SPLIT_V partial implementations (#19433) tlopex
2026/04/28 (tvm) branch main updated: [REFACTOR][IR] Migrate include/tvm/node into include/tvm/ir (#19463) bohan
2026/04/28 (tvm-ffi) tag v0.1.11-rc1 deleted (was 899c5fb) yaxingcai
2026/04/28 (tvm-ffi) tag v0.1.11-rc2 created (now 3c35034) yaxingcai
2026/04/27 (tvm) branch nightly updated (b7c85e3a53 -> 11ac2ad97c) github-bot
2026/04/27 (tvm-site) branch asf-site updated: deploying docs (apache/tvm@11ac2ad97c84fdc6ca14690a6221e9f3d1631955) tqchen
2026/04/27 (tvm) branch main updated: [REFACTOR][NODE] Use fn_repr inside kRepr lambdas, not ffi::ReprPrint (#19462) tqchen
2026/04/27 (tvm) branch main updated: [REFACTOR][RUNTIME] Phase out profiling.h heavy types, rename to timer.h (#19455) tqchen
2026/04/27 (tvm) branch main updated: [REFACTOR][RUNTIME] Macro cleanup — TVM_DLL alignment, [[maybe_unused]], logging.h legacy macros (#19457) tqchen
2026/04/27 (tvm) branch main updated: [REFACTOR][S-TIR] Minimize src/support/ by relocating s_tir-private headers (#19460) tqchen
2026/04/27 (tvm) branch main updated: [Relax][Frontend][TFLite] Add soft-NMS support for TFLite NON_MAX_SUPPRESSION_V5 (#19426) tlopex
2026/04/27 (tvm) branch main updated: [REFACTOR] Phase out src/support/ffi_testing.cc (#19459) tqchen
2026/04/27 (tvm) branch main updated: [REFACTOR][NODE] Migrate ReprPrinter to tvm-ffi __ffi_repr__ mechanism (#19461) tlopex
2026/04/27 (tvm) branch main updated: [REFACTOR] Move source_utils.h into runtime/opencl (#19456) bohan
2026/04/27 (tvm) branch main updated: [REFACTOR] Phase out unreachable contrib/rust_extension.cc (#19458) bohan
2026/04/27 (tvm) branch main updated: [BugFix][Relax][ONNX] Honor auto_pad in ConvTranspose converter (#19450) tlopex
2026/04/27 (tvm) branch main updated: [REFACTOR][CODEGEN] Phase out tvm_global_barrier_state and tvm_prepare_global_barrier (#19454) tlopex
2026/04/26 (tvm) branch nightly updated (daefffcace -> b7c85e3a53) github-bot
2026/04/26 (tvm) branch main updated: [REFACTOR] Use FFI types in runtime inline module-create wrapper signatures (#19449) tlopex
2026/04/26 (tvm) branch ffi-compat-module-create-signatures deleted (was deb878107a) tqchen
2026/04/26 (tvm) branch ffi-compat-module-create-signatures created (now deb878107a) tqchen
2026/04/26 (tvm) 01/01: [REFACTOR] Use FFI types in runtime inline module-create wrapper signatures tqchen
2026/04/26 (tvm) branch target deleted (was e66d7d67df) tqchen
2026/04/26 (tvm) branch refactor-docker-bash-sh deleted (was 5e98b4ac67) tqchen
2026/04/26 (tvm) branch revert-18925-fix/pickle-memoize-unsafe-load deleted (was 23de675df2) tqchen
2026/04/26 (tvm) branch split-libtvm-runtime-compiler deleted (was 21f42fc62c) tqchen
2026/04/26 (tvm) branch isolate-module-create-registry deleted (was e4cef76fc9) tqchen
2026/04/26 (tvm) branch jenkins-s3-bundle-refactor deleted (was 3230418351) tqchen
2026/04/26 (tvm) branch main updated: [TIR] Update symbolic index term order in loop fusion (#18406) tlopex
2026/04/26 (tvm) branch main updated: [REFACTOR] Isolate backend module creation via ffi.Module.create.<kind> registry (#19447) bohan