## What's Changed
* [TEST] Relax test_shared_dag_hash_scaling_not_exponential ratio to 4x by 
@tqchen in https://github.com/apache/tvm-ffi/pull/612
* chore(release): Version bump after release v0.1.12 by @MasterJH5574 in 
https://github.com/apache/tvm-ffi/pull/617
* [FEAT] Add structural visitor and typed structural walk APIs by @Kathryn-cat 
in https://github.com/apache/tvm-ffi/pull/601
* Robustify FromJSONGraph by @tqchen in 
https://github.com/apache/tvm-ffi/pull/619
* [REFACTOR][STUBGEN] refactor the stubgen logic. by @Seven-Streams in 
https://github.com/apache/tvm-ffi/pull/608
* Adopt AGENTS.md for agent guidance by @tqchen in 
https://github.com/apache/tvm-ffi/pull/620
* [DOCS] Document Python FFI conversion protocols by @tqchen in 
https://github.com/apache/tvm-ffi/pull/622
* [CI] Update astral-sh/setup-uv to allowed ref v8.2.0 by @cyx-6 in 
https://github.com/apache/tvm-ffi/pull/624
* [DOCS] Clarify CStrParts error handling usage by @tqchen in 
https://github.com/apache/tvm-ffi/pull/625
* [CI] Bump pinned GitHub Action hashes by @tqchen in 
https://github.com/apache/tvm-ffi/pull/626
* [BUILD] Hide symbols from linked static libraries by @tqchen in 
https://github.com/apache/tvm-ffi/pull/627
* [CMake] Format static symbol helper condition by @tqchen in 
https://github.com/apache/tvm-ffi/pull/628
* Avoid unused type_index local in structural visit by @tqchen in 
https://github.com/apache/tvm-ffi/pull/629
* [FIX] Avoid -Wassume error in structural visit VisitImpl by @cyx-6 in 
https://github.com/apache/tvm-ffi/pull/632
* [CI] Update Jimver/cuda-toolkit to allowed ref v0.2.35 by @cyx-6 in 
https://github.com/apache/tvm-ffi/pull/631
* [CI] Phase out Python 3.8 wheel builds by @tqchen in 
https://github.com/apache/tvm-ffi/pull/633
* [CI] Ignore existing DLLs in Windows wheel repair by @tqchen in 
https://github.com/apache/tvm-ffi/pull/635
* [OBJECT] Optimize dynamic RuntimeTypeIndex loads by @tqchen in 
https://github.com/apache/tvm-ffi/pull/634
* [OBJECT] Make object info macro compatible with CRTP by @tqchen in 
https://github.com/apache/tvm-ffi/pull/636
* [CORE] Invert object/type_traits dependency layering by @tqchen in 
https://github.com/apache/tvm-ffi/pull/638
* [API] Add type index query mode by @tqchen in 
https://github.com/apache/tvm-ffi/pull/640
* [FFI] Add ref-qualified strict ObjectRef casts by @tqchen in 
https://github.com/apache/tvm-ffi/pull/639
* [PY] Distinguish FFI input and output annotations by @Ubospica in 
https://github.com/apache/tvm-ffi/pull/621
* [PY] Support pickling FFI String and Bytes by @Ubospica in 
https://github.com/apache/tvm-ffi/pull/643
* [FFI] Make StructuralEqual functor compare tensor content by @pisarev in 
https://github.com/apache/tvm-ffi/pull/646
* [CORE] Add type subsumption and object-ref containment relations by @tqchen 
in https://github.com/apache/tvm-ffi/pull/647
* Include torch build/ABI in torch C-DLPack addon cache key by @tugot17 in 
https://github.com/apache/tvm-ffi/pull/644
* [FEAT][RUST]Add tvm_ffi::Map in Rust by @Seven-Streams in 
https://github.com/apache/tvm-ffi/pull/623
* [FIX] Make object construction exception-safe by @tqchen in 
https://github.com/apache/tvm-ffi/pull/650
* [FEAT][RUST]Add tvm_ffi::optional in Rust by @Seven-Streams in 
https://github.com/apache/tvm-ffi/pull/630
* [FIX] Resolve JIT GPU backend by explicit signals, not stray /opt/rocm by 
@tqchen in https://github.com/apache/tvm-ffi/pull/652
* [TEST] Run the Python test suite in parallel with a shared GPU lock by 
@tqchen in https://github.com/apache/tvm-ffi/pull/654
* [FIX] Mark ObjectRef throw-only paths unreachable by @tqchen in 
https://github.com/apache/tvm-ffi/pull/656
* [FFI] Back Optional and Variant by TVMFFIAny for a stable ABI layout by 
@tqchen in https://github.com/apache/tvm-ffi/pull/657
* [ORCJIT] Reinject contexts on first function lookup by @tqchen in 
https://github.com/apache/tvm-ffi/pull/655
* [ORCJIT] Add shared session and high-level load_module by @cyx-6 in 
https://github.com/apache/tvm-ffi/pull/658
* [ORCJIT] Embed liborc_rt into the extension and add orc_rt selector by @cyx-6 
in https://github.com/apache/tvm-ffi/pull/660
* build(python)!: require CMake 3.26 for ABI-aware builds by @junrushao in 
https://github.com/apache/tvm-ffi/pull/661
* refactor(dataclasses)!: separate field resolution and native lifetimes by 
@junrushao in https://github.com/apache/tvm-ffi/pull/663
* refactor(enum)!: unify native enum state and singleton conversion by 
@junrushao in https://github.com/apache/tvm-ffi/pull/664
* feat(core): support ObjectPtr in FFI type traits by @junrushao in 
https://github.com/apache/tvm-ffi/pull/665
* feat(dtype): expand parsing and introspection by @junrushao in 
https://github.com/apache/tvm-ffi/pull/668
* ci(lint): run hooks through the uv development environment by @junrushao in 
https://github.com/apache/tvm-ffi/pull/669
* feat(abi): generate layout-compatible C++ object declarations by @junrushao 
in https://github.com/apache/tvm-ffi/pull/670
* [FEAT][Python] Tie Python wrapper lifetime to underlying C++ FFI object by 
@cyx-6 in https://github.com/apache/tvm-ffi/pull/593
* fix(device): require canonical Python device names by @tqchen in 
https://github.com/apache/tvm-ffi/pull/671
* fix(packaging): tag core wheels per-version instead of abi3 by @cyx-6 in 
https://github.com/apache/tvm-ffi/pull/672
* [FEAT] Add Expected<void> specialization by @Kathryn-cat in 
https://github.com/apache/tvm-ffi/pull/673
* fix(reflection): require exact field and method name matches by @Kathryn-cat 
in https://github.com/apache/tvm-ffi/pull/674

## New Contributors
* @Seven-Streams made their first contribution in 
https://github.com/apache/tvm-ffi/pull/608
* @pisarev made their first contribution in 
https://github.com/apache/tvm-ffi/pull/646
* @tugot17 made their first contribution in 
https://github.com/apache/tvm-ffi/pull/644

**Full Changelog**: 
https://github.com/apache/tvm-ffi/compare/v0.1.12...v0.1.13-rc0

-- 
View it on GitHub:
https://github.com/apache/tvm-ffi/releases/tag/v0.1.13-rc0
You are receiving this because you are subscribed to this thread.

Message ID: <apache/tvm-ffi/releases/[email protected]>

Reply via email to