e479a5dbe7
[RUNTIME][PYTHON] Add explicit Target device conversion ( #20005 )
...
## Summary
Compiler Targets can carry device-type semantics that runtime
device-name parsing does not preserve.
- add `tvm.device_from_target` for canonical Target-to-Device
translation
- use explicit runtime constructors where the device kind is fixed
- update target-derived utilities, tests, and documentation to use the
explicit boundary
2026-07-15 05:34:21 +08:00
08f7d9b984
[Relax] Use optional dtype for absent Relax dtype fields ( #19890 )
2026-06-26 10:15:49 -04:00
c9fb8cd3cd
[Docs] Clean up stale references from recent refactors ( #18908 )
...
This is a follow-up pr of #18906
- **Removed "Unity" branding**: Replace "Apache TVM Unity" with "Apache
TVM" across all docs (Unity branch has been merged into
main)
- **Fixed stale Python APIs**: `tvm.instrument` → `tvm.ir.instrument`,
`tvm.transform` → `tvm.ir.transform`, `tvm.module.Module` →
`tvm.runtime.Module`, `tvm.convert` → `tvm.runtime.convert`,
`tvm.runtime.load` → `tvm.runtime.load_module`
- **Fixed S-TIR migration**: `tvm.tir.transform.DefaultGPUSchedule` →
`tvm.s_tir.transform.DefaultGPUSchedule`; added missing
`s_tir/transform` API doc page
- **Removed references to deleted features**: AutoTVM/AutoScheduler
(removed), FewShotTuning (phased out in #18864 ), i386 CI
(removed in #18737 ), VTA (removed), TensorFlow frontend (not in Relax),
MXNet/Gluon (archived)
- **Fixed stale C++ references**: `NodeRef` → `ObjectRef`, `make_node` →
`ffi::make_object`, removed unused `using
tvm::runtime::Registry`, `src/relax/transforms/` →
`src/relax/transform/`
- **Updated CI docs**: Added GitHub Actions lint workflow info to
`ci.rst`
- **Fixed broken links**: dead tutorial links in `pass_infra.rst`,
`gallery/` → `docs/how_to/tutorials/`, `how-to/index.rst` →
`how_to/dev/index.rst`, `discuss.tvm.ai` → `discuss.tvm.apache.org`
- **Updated overview**: TensorFlow → ONNX in supported framework list,
AutoTVM → RPC in security docs
2026-03-18 13:57:14 -04:00
33dcea1686
[REFACTOR][LINT] Modernize ruff config ( #18810 )
...
This PR removes the extra lint violations from the codebase so lint
aligns with the latest style
2026-02-23 07:29:21 -05:00
aa2e609136
[LINT] Modernize lint to use pre-commit hooks ( #18807 )
...
This PR migrates existing lint to use pre-commit hooks
2026-02-22 11:03:21 -05:00
adda179705
[REFACTOR][S-TIR] Lift dlight into s_tir namespace ( #18734 )
...
This PR migrates dlight into s_tir namespace, so s_tir related
components are closely grouped together.
2026-02-08 20:20:11 -05:00
17074cd83d
[DOC] Fix grammar ( #18731 )
...
Fix grammar issues in 'quick_start.py'
2026-02-08 10:42:43 -05:00
543e64dbb1
[FFI][REFACTOR] Cleanup tvm_ffi python API and types ( #18277 )
...
This PR cleans up the python API to make things more consistent
with existing python array api and torch.
Device update
- device_id => index, to be consistent with torch
- device_type => dlpack_device_type() returns int
- added type property same as torch.device
API updates:
- Move the convenient method like cpu() out into tvm runtime to keep device minimal
- tvm_ffi._init_api => tvm_ffi.init_ffi_api
- tvm_ffi.register_func => tvm_ffi.register_global_func
2025-09-07 10:38:50 -04:00
3c36ce2ec6
[FFI][REFACTOR][ABI] Rename NDArray to Tensor ( #18275 )
...
This PR Updates the NDArray => Tensor.
Both tensor and ndarray are commonly used terms.
Because the term Tensor is getting more common in the context of ML,
we do the rename to stay more aligned with torch.Tensor and DLTensor.
2025-09-06 14:33:59 -07:00
be8e43814a
[Refactor] Migrate build API to tvm.compile ( #17718 )
...
* tvm.build -> tvm.compile
* relax.build -> tvm.compile
* update
2025-03-09 07:23:52 -04:00
001d5ec90c
[Relax][PyTorch][Docs] Use torch.export insteamd of fx.symbolic_trace for tutorial ( #17436 )
...
* use torch.export
* in order to make interface consistent, user inputs should be placed first
* chore
2024-10-07 20:57:27 -04:00
e1da4651df
[Doc] IRModule ( #17298 )
2024-08-23 08:05:55 -04:00
32063b0dfc
[Doc] Quick Start ( #17289 )
...
This PR introduces a new quick start tutorial to the documentation.
2024-08-22 10:24:23 -04:00
Tianqi Chen