Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
404 commits
Select commit Hold shift + click to select a range
635e8c3
rebase
LeiWang1999 Oct 22, 2025
548cadf
merge rebase
LeiWang1999 Oct 22, 2025
d7f0118
rebase fix
LeiWang1999 Oct 22, 2025
a78f6f5
rebase fix
LeiWang1999 Oct 22, 2025
ea34153
Remove dlpack submodule
LeiWang1999 Oct 23, 2025
3345fde
rebasefix
LeiWang1999 Oct 23, 2025
3085bc4
Refactor GCD computation and update annotation merging to use ffi::Ma…
LeiWang1999 Oct 23, 2025
0f1ebab
bug fix
LeiWang1999 Oct 23, 2025
e28b510
Add VisitStmt_ method for AssertStmtNode and StringImmNode (#18389)
jikechao Oct 24, 2025
9274761
[Relax][PyTorch] Add run_ep_decomposition flag to control PyTorch dec…
tlopex Oct 26, 2025
356cb57
fix the 8-bit vector loads/stores problem, which will solve the prob…
hantao-zhou Oct 26, 2025
d3bb716
[Relax][PyTorch] Add support for decomposed operators in extended una…
tlopex Oct 27, 2025
30fcca2
Support integer types in exp TIR expression operator (#18390)
jikechao Oct 27, 2025
68854d6
[Relax][PyTorch] Enable decomposition for unary ops and refactor test…
tlopex Oct 28, 2025
f532b89
[Relax][PyTorch] Add support for decomposed operators and fix IR of o…
tlopex Oct 29, 2025
be37afd
[Relax][PyTorch] Add support for decomposed operators and fix IR of o…
tlopex Oct 30, 2025
bda2ec7
Fixing database bug (#18409)
thaisacs Oct 30, 2025
00f7d7b
fix type linting warning in tl.float32
kurisu6912 Oct 27, 2025
fa576ec
Merge branch 'tilelang_main' of https://github.com/TileLang/tvm into …
LeiWang1999 Oct 31, 2025
c4d01b5
[FFI] Bump tvm-ffi to latest (#18411)
tqchen Nov 1, 2025
36a4696
[DOCS] Add tutorial for exporting and loading back Relax executables …
tlopex Nov 1, 2025
9249061
[Relax][PyTorch] Add support for decomposed operators and fix IR of o…
tlopex Nov 1, 2025
8f1145d
[DOCS] Update tutorial for exporting and loading back Relax executabl…
tlopex Nov 2, 2025
a57f651
Add support for finding PrimFuncFrame in buffer allocation
LeiWang1999 Nov 2, 2025
1815c3e
Merge branch 'tilelang_main' of https://github.com/TileLang/tvm into …
LeiWang1999 Nov 2, 2025
5ca61bb
[Relax][PyTorch] Add support for decomposed operators and fix IR of o…
tlopex Nov 3, 2025
1e28bf9
[Relax][ONNX] Fix bug: Unsupported numpy or ml_dtypes dtype('O') when…
cchung100m Nov 3, 2025
03d55df
[Relax][PyTorch] Add support for decomposed operators and fix IR of o…
tlopex Nov 4, 2025
8ab96af
[TEST] Refactor: remove the deprecated warning message check from tes…
cchung100m Nov 5, 2025
ae83984
[Relax][PyTorch] Add support for decomposed operators and fix IR of o…
tlopex Nov 6, 2025
3d13658
[DOCS] Update cross-compilation and RPC tutorial with modern PyTorch …
tlopex Nov 6, 2025
33fa926
[Relax][PyTorch] Add support for decomposed operators and fix IR of o…
tlopex Nov 9, 2025
bfb0dd6
[Relax][PyTorch] Add support for decomposed operators and fix IR of o…
tlopex Nov 10, 2025
26db8bf
[Web] Fix arrayDecodeStorage scope issue for q0f32 models (#18415)
akaashrp Nov 10, 2025
f574031
[TEST][CODEGEN] Fix the test scripts tries to tell numpy a dtype name…
cchung100m Nov 11, 2025
2e24fc1
Add VisitBitwiseXor method to ConstIntBoundAnalyzer for handling bitw…
LeiWang1999 Nov 12, 2025
394f668
[Relax][Pytorch] Support basic range constraints (#18429)
guan404ming Nov 12, 2025
1b54bb0
Add VisitBitwiseOr method to ConstIntBoundAnalyzer for handling bitwi…
LeiWang1999 Nov 12, 2025
f0bbd3b
remove 3rdparty
LeiWang1999 Nov 12, 2025
093b2cd
Remove dlpack subproject from 3rdparty directory
LeiWang1999 Nov 12, 2025
ce5f287
[Relax][PyTorch] Add support for decomposed operators and fix IR of o…
guan404ming Nov 12, 2025
d013dad
[TOPI] Support integer type input for log and log2 (#18426)
jikechao Nov 12, 2025
4b555a9
Adjusted Longrope embedding function to match Huggingface Implementat…
babusid Nov 12, 2025
6785c8f
[CI] Enable username checks in PR title and body (#18432)
guan404ming Nov 13, 2025
506a0bb
[Relax][PyTorch] Add decomposed operator support for AdaptiveAvgPool …
guan404ming Nov 13, 2025
e5fb395
[Relax][PyTorch] Add decomposed operator support for MaxPool (#18446)
guan404ming Nov 14, 2025
0754ad8
[FRONTEND][ONNX] Fix operator Transpose: TVMError: PermuteDims expect…
cchung100m Nov 14, 2025
ce0ac66
[Relax][PyTorch] Add lower bound support for range constraints (#18447)
guan404ming Nov 14, 2025
2523ee1
[CI] Update pre-commit configuration (#18448)
guan404ming Nov 14, 2025
cdc2ace
Refactor CUDA function attribute setting and enhance error message ha…
LeiWang1999 Nov 14, 2025
1134778
[DOCS] Remove prebuilt package references and disable Colab button at…
tlopex Nov 14, 2025
6c7ed24
[DOCS] Update the merge setting (#18451)
tqchen Nov 14, 2025
f8471f8
[Relax][PyTorch] Add decomposed operator support for Pad (#18449)
guan404ming Nov 14, 2025
b6ac072
[DataType] Update to use explicit Bool Type Aligning with DLPack (#18…
tqchen Nov 15, 2025
45a2a40
[Relax][PyTorch] Add decomposed operator support for Binary (#18458)
guan404ming Nov 15, 2025
a9955e5
[Relax][PyTorch] Add decomposed operator support for normalization (#…
guan404ming Nov 16, 2025
0225d67
[Relax][PyTorch] Fix MultiheadAttention complie (#18459)
guan404ming Nov 16, 2025
f4105f8
Enhance find_include_path function to include system-installed tvm_ff…
LeiWang1999 Nov 16, 2025
fd57110
[CI] Fix crash when grep finds no matches (#18457)
guan404ming Nov 16, 2025
0701aab
[Relax][PyTorch]: Fix the sqrt operation requires float dtype but rec…
cchung100m Nov 16, 2025
ea89f21
[Relax][PyTorch] Support advanced range constraints (addition) (#18452)
guan404ming Nov 17, 2025
8dc9f5f
[Relax][PyTorch] Fix KeyError: dtype when converting PyTorch model wi…
cchung100m Nov 17, 2025
83db389
[Relax][PyTorch] Enable decomposition in all tests (#18464)
guan404ming Nov 18, 2025
49973d1
[Relax][PyTorch] Support advanced range constraints (multiplication) …
guan404ming Nov 18, 2025
5d8c4d2
[Web] Fix progress reporting when loading from cache (#18450)
mihailyonchev Nov 18, 2025
ebd169b
[Relax] Fix flaky test_conv2d_offload by increasing float32 tolerance…
tlopex Nov 18, 2025
49e650b
[DataType] Update to use explicit Bool Type Aligning with DLPack (#18…
tqchen Nov 15, 2025
f4affc7
Revert "[DataType] Update to use explicit Bool Type Aligning with DLP…
LeiWang1999 Nov 19, 2025
6dc71f3
[Relax][PyTorch] Add decomposed operator support for interpolate (#18…
guan404ming Nov 19, 2025
2adf5ea
Reapply "[DataType] Update to use explicit Bool Type Aligning with DL…
LeiWang1999 Nov 19, 2025
12f3bb0
[Contrib] Update RandomFill to use StreamSync for CUDA synchronizatio…
guan404ming Nov 20, 2025
b2c58ef
[TIR] Fix Data Type Mismatch (int64 vs int32) in T.match_buffer when …
cchung100m Nov 20, 2025
18a30cd
Relax constraint side effect check in EnterConstraint (#14)
LJC00118 Nov 20, 2025
a8c7580
[Relax][PyTorch] Enable run_ep_decomposition by default (#18471)
guan404ming Nov 20, 2025
70808bc
Implement dynamic shared memory handling in CUDA kernel launches. Tra…
LeiWang1999 Nov 20, 2025
7e4da6d
Merge branch 'tilelang_main' of https://github.com/TileLang/tvm into …
LeiWang1999 Nov 20, 2025
713e6ad
Revert "Reapply "[DataType] Update to use explicit Bool Type Aligning…
LeiWang1999 Nov 20, 2025
c8515e1
[Web] Replace string with TVMFFIByteArray* to avoid memory issues (#1…
akaashrp Nov 20, 2025
4a60bb2
[Relax][PyTorch] Add support for `torch.ops.aten.sym_size.int` in Exp…
mshr-h Nov 21, 2025
ead90f6
Add missing int32x2 and other dtypex2
kurisu6912 Nov 21, 2025
bc31e7a
remove unused let_binding_ in CodeGenC
kurisu6912 Nov 21, 2025
3eb4938
Support analyzer clone
LeiWang1999 Nov 21, 2025
cd2b2b6
Merge branch 'tilelang_main' of https://github.com/TileLang/tvm into …
LeiWang1999 Nov 21, 2025
bf8a907
[Relax][PyTorch] Add dynamic shape support to `torch.ops.aten.sym_siz…
mshr-h Nov 21, 2025
cdca134
[Relax][PyTorch] Add support for gumbel_softmax (#18482)
guan404ming Nov 21, 2025
41a606c
[Relax][PyTorch] Add support for grid_sample operator (#18483)
guan404ming Nov 21, 2025
d982a43
[Web] Bump web runtime version 0.23.0-dev1 (#18480)
akaashrp Nov 22, 2025
c44088d
[Relax][PyTorch] Fix `batch_norm.default` args handling in ExportedPr…
mshr-h Nov 22, 2025
b466ef5
[Relax][PyTorch] Enhance index_put support for multi-dimensional indi…
guan404ming Nov 22, 2025
5099068
[Relax][PyTorch] Add `count_include_pad` support to `avg_pool2d` in P…
mshr-h Nov 23, 2025
b01dadb
[Relax][PyTorch] Add `as_strided` operator in ExportedProgram fronten…
mshr-h Nov 23, 2025
5a6e977
[CI] Update `actions/cache` to v4 in setup action (#18495)
mshr-h Nov 23, 2025
8660e40
[Relax][PyTorch] Add broadcast support for `copy` operation (#18493)
mshr-h Nov 23, 2025
b4e0d3e
[Relax][PyTorch] Add negative slicing support in `slice_scatter` oper…
mshr-h Nov 23, 2025
7e6165e
Fix BufferError when converting PyTorch models with sparse tensors (#…
Dayuxiaoshui Nov 23, 2025
3354ada
disable narrowing uint in NarrowDataType pass
kurisu6912 Nov 24, 2025
97d78aa
[Relax][PyTorch] Add `mul` operator in ExportedProgram frontend (#18496)
mshr-h Nov 24, 2025
faab2e7
[Relax] Fix the squeeze operator to behave consistently with torch (#…
ConvolutedDog Nov 24, 2025
2032e71
[TIR][Schedule] Add FuseReductionEpilogue primitive to fuse epilogue …
kimm240 Nov 24, 2025
0bd6f9c
[CI] Use glob for `conda/build-environment.yaml` in cache key (#18498)
mshr-h Nov 24, 2025
91c1921
[Relax][PyTorch] Add binary operation dtype promotion following PyTor…
mshr-h Nov 24, 2025
9e905f9
[CI] Enhance python linting scripts to support revision-based checks …
guan404ming Nov 24, 2025
13ea9dc
[TIR] Add step attribute to ForNode (Initial codes) (#18421)
wrongtest-intellif Nov 24, 2025
4be951d
[RELAX][PASS] Annotate Custom Scope layout pass for Adreno GPU (#17599)
srkreddy1238 Nov 24, 2025
e3af400
disable strided buffer load in tvm
kurisu6912 Nov 25, 2025
9826150
[TIR]: Fix VerifyStream::Verify causes dereferencing an invalid point…
cchung100m Nov 25, 2025
ced7181
[TVMScript] Add block name suffix management for TIR macros (#18465)
guan404ming Nov 25, 2025
161049e
[Relax][PyTorch] Enhance handling of unbounded upper bound constraint…
guan404ming Nov 26, 2025
ec7f59f
[TVMScript] Add test for TIR macro block name suffix handling (#18504)
guan404ming Nov 26, 2025
6041e9f
[Relax][PyTorch] Add support for antialiased bilinear upsampling (#18…
guan404ming Nov 26, 2025
6e0d4d5
[MISC] Fix compilation warnings (#18509)
Hzfengsy Nov 26, 2025
c3a52ea
[TIR] Update function signatures for decompose_reduction (#18505)
guan404ming Nov 26, 2025
843a574
[MISC] Remove unused TVMC configs (#18512)
Hzfengsy Nov 26, 2025
9545b3c
[Relax][PyTorch] Support specifying decimals for _round (#18507)
guan404ming Nov 27, 2025
316299d
[Relax][PyTorch] Enhance data type handling in FX graph translator (#…
guan404ming Nov 27, 2025
e3c5b47
[Relax][PyTorch] Unify tests using shared verify_model (#18517)
guan404ming Nov 27, 2025
790c5d1
[Pass] Add DumpIR pass instrument to save IR snapshots (#18511)
Hzfengsy Nov 27, 2025
d5d3d81
[Relax][PyTorch] Fix batch normalization training mode correctness (#…
guan404ming Nov 27, 2025
7fe8760
[TIR] Fix tir.LowerIntrin check failed additional_info.size() == new_…
cchung100m Nov 28, 2025
25a37e7
[Relax][PyTorch] Add support for sparse matrix multiplication and ran…
Dayuxiaoshui Nov 28, 2025
fc7ed0b
Fix const correctness issues when assigning string literals to Any un…
LeiWang1999 Nov 28, 2025
e633295
integrate z3 with tvm
kurisu6912 Nov 28, 2025
075e08a
Merge commit 'fc7ed0b9c' into z3
kurisu6912 Nov 28, 2025
1c77db7
[Relax][PyTorch] Add support for bidirectional LSTM (#18516)
guan404ming Nov 28, 2025
acda952
[Relax][PyTorch] Unify tests using shared tvm.testing.assert_allclose…
guan404ming Nov 29, 2025
ca19be8
[Relax][PyTorch] Add support for binary scalar operations in Exported…
mshr-h Nov 29, 2025
fc2bdfe
[Relax][PyTorch] Add support for non-persistent buffers in ExportedPr…
mshr-h Nov 29, 2025
45ab5fb
[Relax][PyTorch] Fix InternalError when converting scaled_dot_product…
Dayuxiaoshui Nov 29, 2025
4244a86
[Relax][PyTorch] Add boolean tensor support for max operation and cor…
mshr-h Nov 29, 2025
934c4a4
[Relax][PyTorch] Add support for bidirectional GRU (#18532)
guan404ming Nov 30, 2025
c429a2b
[CI] Update file patterns for specific linting hooks (#18484)
guan404ming Nov 30, 2025
54c3fb4
[Relax][PyTorch] Handle unknown output shapes for _sym_size_int (#18521)
guan404ming Nov 30, 2025
d6e6334
[Bugfix] Prevent segfault when instantiating abstract SearchStrategy …
Dayuxiaoshui Dec 1, 2025
ec0026e
[Relax][PyTorch] Fix index_put with broadcast indices (#18533)
guan404ming Dec 1, 2025
e8b0261
Remove debug print statements from PyStmtExprVisitor methods to clean…
LeiWang1999 Dec 2, 2025
50ec055
Merge commit 'e8b02611f' into HEAD
kurisu6912 Dec 2, 2025
f86ab53
fix many bugs in z3_prover
kurisu6912 Dec 2, 2025
36e4074
Add better debug print functionality
kurisu6912 Dec 2, 2025
1be49b8
Enhance Z3 prover and analyzer integration with improved constraints …
kurisu6912 Dec 3, 2025
7517ab6
Add methods to set Z3 max step and retrieve Z3 statistics in Analyzer
kurisu6912 Dec 3, 2025
cd820b5
[ARITH] Fix InternalError: Check failed: (eval_vec_) is false (#18536)
cchung100m Dec 3, 2025
ed97234
Revert "[ARITH] Fix InternalError: Check failed: (eval_vec_) is false…
tlopex Dec 4, 2025
c71aefc
[Docs] Fix e2e_opt_model tutorial for GPU deployment (#18539)
tlopex Dec 4, 2025
001ed57
[Schedule] Fix LocalBuilder Check failed: (index_map_func.has_value()…
Asuka0630 Dec 4, 2025
141431c
[TIR][Schedule] Fix mma tensorize error (#18528)
Asuka0630 Dec 4, 2025
a747614
[Relax][PyTroch] Add NHWC layout support (#18548)
guan404ming Dec 5, 2025
4c2249d
[CI] Remove hardcoded user and repo values (#18549)
guan404ming Dec 5, 2025
3a32b76
introduce var_lca
LeiWang1999 Dec 5, 2025
5138efc
[Relax][PyTorch] Unify dtype used in conv2d tests (#18553)
guan404ming Dec 6, 2025
6cf49e6
[Relax][PyTorch] Enhance scale_factor handling in interpolation (#18550)
guan404ming Dec 6, 2025
0d9d178
[MISC] Fix duplicate `PresburgerSetNode` registration when `USE_MLIR=…
mshr-h Dec 6, 2025
dcecb86
[Docs] Improve static shape tuning parameter configuration (follow-up…
ConvolutedDog Dec 6, 2025
2b4a1e2
[Relax][Frontend] Introduce ModuleDict (#18551)
mshr-h Dec 7, 2025
26b107f
[Relax][PyTorch] Add support for masked_select (#18535)
guan404ming Dec 7, 2025
0297c0b
Make z3 an optional dependency
kurisu6912 Dec 8, 2025
250827c
make z3 an optional feature
kurisu6912 Dec 8, 2025
0b352a1
build system debug
kurisu6912 Dec 8, 2025
3a8b894
build system debug
kurisu6912 Dec 8, 2025
e6f891c
build system debug
kurisu6912 Dec 8, 2025
7019e85
build system debug
kurisu6912 Dec 8, 2025
46c5427
build system debug
kurisu6912 Dec 8, 2025
e6a6694
build system debug
kurisu6912 Dec 8, 2025
a6088da
build system debug
kurisu6912 Dec 8, 2025
68f5e91
Merge commit '3a32b763e' into z3
kurisu6912 Dec 8, 2025
877f20c
add ,ossomg z3_header dependency
kurisu6912 Dec 8, 2025
e78fbd8
[Attn] Fix calling FlashInfer attention plan function (#18557)
MasterJH5574 Dec 8, 2025
bddc091
[TIR][Schedule] Fix bug on bfloat16 conversion (#18556)
grf53 Dec 8, 2025
7271feb
[Relax][PyTorch] Add support for Custom Ops for ExportedProgram front…
mshr-h Dec 9, 2025
8218b18
[Relax] Add mod operator support (#18559)
guan404ming Dec 9, 2025
04f06b5
[Relax] Add edge padding mode (#18558)
guan404ming Dec 9, 2025
85a8770
[Relax] Enhance unique block name generation with numeric suffixes (#…
guan404ming Dec 10, 2025
a9c22ee
Add structured boolean reasoning in Analyzer::CanProve method
LeiWang1999 Dec 10, 2025
90581fe
Merge branch 'tilelang_main' of https://github.com/TileLang/tvm into …
LeiWang1999 Dec 10, 2025
afc0793
Merge branch 'main' of https://github.com/apache/tvm into tilelang_main
LeiWang1999 Dec 10, 2025
2b1ead1
Implement relaxed PrimFuncFrame retrieval in IRBuilder
LeiWang1999 Dec 12, 2025
e9f9392
use statically linked z3
kurisu6912 Dec 12, 2025
dd834fd
merge branch z3 into tilelang_main
kurisu6912 Dec 12, 2025
afb0370
update z3 build steps
kurisu6912 Dec 12, 2025
f6bcb0b
update build include directory
kurisu6912 Dec 12, 2025
cb9736f
update build system
kurisu6912 Dec 12, 2025
1059552
fix bug in build system
kurisu6912 Dec 12, 2025
3537ef7
fix bug in build system
kurisu6912 Dec 12, 2025
185bba7
minor fix
kurisu6912 Dec 12, 2025
790e793
Enhance IRConvertSSA to handle container types in VisitExpr
LeiWang1999 Dec 14, 2025
68aa846
Merge branch 'tilelang_main' of https://github.com/TileLang/tvm into …
LeiWang1999 Dec 14, 2025
20a5922
fix bool bug in z3
kurisu6912 Dec 15, 2025
d730446
remove z3
kurisu6912 Dec 15, 2025
050815c
simplify z3 integration
kurisu6912 Dec 15, 2025
7514242
delete z3 include in z3_prover_off.cc
kurisu6912 Dec 15, 2025
78b4caf
fix z3 for macos (#15)
oraluben Dec 15, 2025
1dde5c8
patch z3 when building tvm
kurisu6912 Dec 15, 2025
d9ccc03
fix typo
kurisu6912 Dec 15, 2025
c43fd9b
add comment to print z3 soname
kurisu6912 Dec 15, 2025
4d3ec92
Merge branch 'z3' into tilelang_main
kurisu6912 Dec 16, 2025
0a7a6ea
Analyzer: require loop extent > 0 when entering loop
kurisu6912 Dec 17, 2025
8f4da61
fix floordiv & floormod converting in z3 prover
kurisu6912 Dec 17, 2025
88778fa
fix when patchelf not found (#16)
oraluben Dec 17, 2025
6dc8b76
use static Z3 context
LeiWang1999 Dec 19, 2025
79ed747
Update Z3 context to be thread-local for improved thread safety
LeiWang1999 Dec 19, 2025
03ad7cc
Update library loading to use lazy loading
LeiWang1999 Dec 19, 2025
1eeadc6
Add cyclic dependency detection in IntervalSetEvaluator
LeiWang1999 Dec 22, 2025
315036d
Merge branch 'tilelang_main' of https://github.com/TileLang/tvm into …
LeiWang1999 Dec 22, 2025
d9d3e9d
Remove Z3 subproject as it is no longer needed in the repository.
LeiWang1999 Dec 22, 2025
62af333
Add a rewrite pattern
kurisu6912 Dec 25, 2025
9bb866e
[Cherry-pick][CUDA][FFI] Extend kernel launch config to support Progr…
silentCoder-dev Dec 26, 2025
ce96c60
[Z3] change z3 timeout to determinstic `rlimit`
kurisu6912 Dec 26, 2025
b487ec4
Merge branch 'tilelang_main' of https://github.com/TileLang/tvm into …
kurisu6912 Dec 26, 2025
8ae9be3
Add annotations to CallNode and Call classes
LeiWang1999 Dec 26, 2025
23bce01
Merge commit '8ae9be35a' into tilelang_main
LeiWang1999 Dec 26, 2025
dcfe86e
Add PrimExpr substitution support for AttrStmt nodes in IRSubstitute …
LJC00118 Dec 31, 2025
25ee6de
fix bug and add functionality for z3 prover
kurisu6912 Jan 6, 2026
e47e76a
Merge branch 'tilelang_main' of https://github.com/TileLang/tvm into …
kurisu6912 Jan 6, 2026
27f8e2f
add escape in codegen c string
kurisu6912 Jan 6, 2026
8bdaa71
Enhance BlockReadWriteDetector to handle exceptions during range anal…
LeiWang1999 Jan 6, 2026
001022b
Merge branch 'tilelang_main' of https://github.com/TileLang/tvm into …
LeiWang1999 Jan 6, 2026
959ece3
add const_int-not (#23)
silentCoder-dev Jan 9, 2026
65ae814
add z3-bitwise (#22)
silentCoder-dev Jan 9, 2026
b82c74d
add bv2int & int2bv for not & shift operation (#24)
silentCoder-dev Jan 12, 2026
da7f19b
fix call with annotations
LeiWang1999 Jan 12, 2026
0794c13
Enhance Call handling by including annotations in various code genera…
LeiWang1999 Jan 13, 2026
b0fc7bf
[Metal] Support using external command buffer to interoperate with to…
oraluben Jan 15, 2026
8935d41
Refactor division and modulus handling to prevent divide-by-zero errors
LeiWang1999 Jan 16, 2026
4a4ff8e
Merge commit '8935d414d' into tilelang_main
LeiWang1999 Jan 16, 2026
2d2039a
fix missing is_assume in analyzer
kurisu6912 Jan 16, 2026
8e0cfc0
Merge branch 'tilelang_main' of https://github.com/TileLang/tvm into …
kurisu6912 Jan 16, 2026
354eef9
Fix missing is_assume in analyzer (#25)
LJC00118 Jan 19, 2026
34fac30
Refactor SSA assignment handling in code generation
LeiWang1999 Jan 22, 2026
bc955a1
Update Z3 prover timeout and enhance logging in CanProve method
LeiWang1999 Jan 29, 2026
8f60c1f
remove unnecessary log from z3
Rachmanino Feb 1, 2026
69db964
Update Z3 prover timeout and fix formatting issues
LeiWang1999 Feb 2, 2026
391d3f7
Enhance conditional handling in code generation (#26)
LeiWang1999 Feb 3, 2026
8d494ca
Add CountSatisfyingValues method to Z3Prover for integer value enumer…
LeiWang1999 Feb 4, 2026
0096781
Refactor access region handling in BlockReadWriteDetector
LeiWang1999 Feb 9, 2026
930c59f
add side effect check in const int bound
kurisu6912 Feb 9, 2026
806ec09
Enhance comparison simplification in RewriteSimplifier
LeiWang1999 Feb 24, 2026
76277e9
Merge branch 'tilelang_main' of https://github.com/TileLang/tvm into …
LeiWang1999 Feb 24, 2026
47c0af2
Support cluster launch for cuda runtime
Rachmanino Feb 26, 2026
ccf2753
support isinfinite
LeiWang1999 Mar 12, 2026
edc1c15
Merge commit '47c0af2' into tilelang_main
LeiWang1999 Mar 12, 2026
470430c
Add artifact path resolution in NVCC compilation and improve TempDire…
LeiWang1999 Mar 12, 2026
016c646
Add EnsureCurrentDeviceContext function for CUDA device management
LeiWang1999 Mar 16, 2026
5c193e1
fix
LeiWang1999 Mar 21, 2026
fab43e4
feat: add bfloat16x2 types (#29)
bucket-xv Mar 26, 2026
12b47d3
fix: ensure positive grid dimensions in CUDA kernel launch
LeiWang1999 Mar 30, 2026
882a774
fix: add cudaGetLastError check after cuLaunchKernel in TVM FFI backe…
kurisu6912 Apr 1, 2026
1c5cdb8
Add tfloat32 datatype (#31)
ColmaLiu Apr 14, 2026
cb75d83
fix llvm compile error (#28)
Lucien0 Apr 14, 2026
329056d
Fix TVMDerivedObject slots for apache-tvm-ffi compatibility (#32)
ChrisLundquist Apr 14, 2026
0e15b27
Fix duplicate __weakref__ declaration in derived_object wrappers (#33)
ColmaLiu Apr 16, 2026
4c55b26
[Metal] emit Metal builtins directly instead of CUDA-style threadIdx/…
apstenku123 May 4, 2026
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
33 changes: 28 additions & 5 deletions .asf.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@
# under the License.

github:
description: "Open deep learning compiler stack for cpu, gpu and specialized accelerators"
description: "Open Machine Learning Compiler Framework"
homepage: https://tvm.apache.org/
labels:
- tvm
Expand All @@ -33,6 +33,12 @@ github:
- spirv
- machine-learning

features:
# Enable issue management
issues: true
# Enable projects for project management boards
projects: true

# Triage perm for collaborators(test run)
#
# The perm is given based on needs and not based on
Expand All @@ -45,10 +51,6 @@ github:
# participation, permission is given on a three month
# cycle. PMC may review and recycle slots when necessary.
collaborators:
- hpanda-naut
- denise-k
- janetsc
- naut-thomas
- tvm-bot # For automated feedback in PR review.

# See https://cwiki.apache.org/confluence/display/INFRA/Git+-+.asf.yaml+features#Git.asf.yamlfeatures-Branchprotection
Expand All @@ -68,3 +70,24 @@ github:

required_pull_request_reviews:
required_approving_review_count: 1

enabled_merge_buttons:
# enable squash button:
squash: true
# default commit message when merging with a squash commit
# can either be: DEFAULT | PR_TITLE | PR_TITLE_AND_COMMIT_DETAILS | PR_TITLE_AND_DESC
squash_commit_message: PR_TITLE_AND_DESC
# enable merge button:
merge: false
# default commit message when merging with a merge commit
# can either be: DEFAULT | PR_TITLE | PR_TITLE_AND_DESC
merge_commit_message: DEFAULT
# enable rebase button for rare use.
rebase: true

notifications:
commits: commits@tvm.apache.org
issues: discuss-archive@tvm.apache.org
pullrequests: discuss-archive@tvm.apache.org
jobs: discuss-archive@tvm.apache.org
discussions: discuss-archive@tvm.apache.org
8 changes: 6 additions & 2 deletions .github/actions/setup/action.yml
Original file line number Diff line number Diff line change
@@ -1,12 +1,12 @@
runs:
using: "composite"
steps:
- uses: actions/cache@v3
- uses: actions/cache@v4
env:
CACHE_NUMBER: 2
with:
path: ~/conda_pkgs_dir
key: ${{ runner.os }}-conda-${{ env.CACHE_NUMBER }}-${{ hashFiles('conda/build-environment.yaml') }}
key: ${{ runner.os }}-conda-${{ env.CACHE_NUMBER }}-${{ hashFiles('**/conda/build-environment.yaml') }}
- uses: conda-incubator/setup-miniconda@v3
continue-on-error: true
id: conda1
Expand Down Expand Up @@ -36,3 +36,7 @@ runs:
mamba list
mamba info --envs
mamba list --name base
- name: Install tvm-ffi pip package
shell: bash -l {0}
run: |
pip install -v ./3rdparty/tvm-ffi
34 changes: 26 additions & 8 deletions .github/workflows/main.yml
Original file line number Diff line number Diff line change
Expand Up @@ -44,11 +44,20 @@ jobs:
submodules: 'recursive'
- name: Set up environment
uses: ./.github/actions/setup
- name: Conda Build
- name: Install LLVM dependencies
shell: bash -l {0}
run: >-
conda build --output-folder=conda/pkg conda/recipe &&
conda install tvm -c ./conda/pkg
run: |
conda install -c conda-forge llvmdev cmake ninja zlib
- name: Build TVM wheel
shell: bash -l {0}
run: |
pip install scikit-build-core
export CMAKE_ARGS="-DUSE_LLVM=ON -DBUILD_TESTING=OFF"
pip wheel --no-deps -w dist . -v
- name: Install TVM from wheel
shell: bash -l {0}
run: |
pip install dist/*.whl
# - name: Build iOS RPC
# run: |
# IOS_VERSION="14.0"
Expand Down Expand Up @@ -98,11 +107,20 @@ jobs:
submodules: 'recursive'
- name: Set up environment
uses: ./.github/actions/setup
- name: Conda Build
- name: Install LLVM dependencies
shell: cmd /C call {0}
run: >-
conda build --output-folder=conda/pkg conda/recipe &&
conda install tvm -c ./conda/pkg
run: |
conda install -c conda-forge llvmdev cmake ninja zlib libxml2-devel
- name: Install TVM
shell: cmd /C call {0}
run: |
pip install scikit-build-core
set CMAKE_ARGS=-DUSE_LLVM=ON -DBUILD_TESTING=OFF
pip install --no-deps . -v
- name: Install test dependencies
shell: cmd /C call {0}
run: |
pip install psutil cloudpickle ml_dtypes numpy packaging scipy tornado typing_extensions
- name: Test
shell: cmd /C call {0}
run: >-
Expand Down
12 changes: 3 additions & 9 deletions .gitmodules
Original file line number Diff line number Diff line change
@@ -1,15 +1,9 @@
[submodule "dmlc-core"]
path = 3rdparty/dmlc-core
url = https://github.com/dmlc/dmlc-core.git
[submodule "dlpack"]
path = 3rdparty/dlpack
url = https://github.com/dmlc/dlpack.git
[submodule "3rdparty/rang"]
path = 3rdparty/rang
url = https://github.com/agauniyal/rang.git
[submodule "3rdparty/libbacktrace"]
path = 3rdparty/libbacktrace
url = https://github.com/tlc-pack/libbacktrace.git
[submodule "3rdparty/cutlass"]
path = 3rdparty/cutlass
url = https://github.com/NVIDIA/cutlass.git
Expand All @@ -28,6 +22,6 @@
[submodule "3rdparty/zlib"]
path = 3rdparty/zlib
url = https://github.com/madler/zlib.git
[submodule "ffi/3rdparty/dlpack"]
path = ffi/3rdparty/dlpack
url = https://github.com/dmlc/dlpack.git
[submodule "3rdparty/tvm-ffi"]
path = 3rdparty/tvm-ffi
url = https://github.com/apache/tvm-ffi
25 changes: 12 additions & 13 deletions .pre-commit-config.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -32,27 +32,26 @@
#

default_language_version:
python: python3.6
python: python3.9
fail_fast: True
default_stages: [push]
default_stages: [pre-push, pre-commit]
repos:
- repo: https://github.com/pre-commit/pre-commit-hooks
rev: v2.3.0
rev: v6.0.0
hooks:
- id: check-added-large-files
- id: check-merge-conflict
- id: check-yaml
- id: end-of-file-fixer
stages: [push]
- id: trailing-whitespace
stages: [push]

- repo: local
hooks:
- id: run-black
name: Running Black...
entry: docker/lint.sh python_format
entry: docker/lint.sh python_format -i
language: system
always_run: true
files: \.py$
pass_filenames: false
- id: run-file-checks
name: Checking File Types....
Expand All @@ -62,25 +61,25 @@ repos:
pass_filenames: false
- id: run-headers-check
name: Checking ASF License Headers ...
entry: docker/lint.sh asf
entry: docker/lint.sh asf -i
language: system
always_run: true
pass_filenames: false
- id: run-headers-check
- id: run-cpplint
name: Linting the C++ code ...
entry: docker/lint.sh cpplint
language: system
always_run: true
files: \.(c|cc|cpp|h|hpp)$
pass_filenames: false
- id: run-clang-format
name: Checking Clang format ...
entry: docker/lint.sh clang_format
entry: docker/lint.sh clang_format -i
language: system
always_run: true
files: \.(c|cc|cpp|h|hpp)$
pass_filenames: false
- id: run-mypy
name: Type Checking with MyPY ...
entry: docker/lint.sh mypy
language: system
always_run: true
files: \.py$
pass_filenames: false
2 changes: 1 addition & 1 deletion 3rdparty/cutlass
Submodule cutlass updated 926 files
1 change: 0 additions & 1 deletion 3rdparty/dlpack
Submodule dlpack deleted from 3ea601
1 change: 0 additions & 1 deletion 3rdparty/libbacktrace
Submodule libbacktrace deleted from 08f7c7
1 change: 1 addition & 0 deletions 3rdparty/tvm-ffi
Submodule tvm-ffi added at ae346e
Loading