-
Notifications
You must be signed in to change notification settings - Fork 4k
Pull requests: apache/tvm
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[Fix][Relax][ONNX] Import Resize with empty scales tensor and symbolic sizes
#20406
opened Sep 22, 2026 by
LiRunGuo
Loading…
[Fix][Relax][Torch] Respect zero-dimensional tensor dtype promotion
#20405
opened Sep 22, 2026 by
jack-k737
Loading…
[Fix][Relax][ONNX] Support symbolic dims in SAME auto_pad pooling
#20404
opened Sep 21, 2026 by
LiRunGuo
Loading…
[REFACTOR][TIR] Represent thread binding as a parallel-loop annotation
#20403
opened Sep 21, 2026 by
tqchen
Member
Loading…
[FIX][Vulkan] Avoid device API destruction during Windows DLL shutdown
#20397
opened Sep 21, 2026 by
sepcnt
Loading…
[Metal] Add TVM_METAL_STORAGE_MODE opt-in for correctness at scale (#20157)
#20391
opened Sep 19, 2026 by
zacharywhitley
Loading…
[Relax] Skip 1-D inputs in CombineParallelMatmul
#20389
opened Sep 19, 2026 by
Nanmur
Contributor
Loading…
[Fix][Relax][Frontend][Torch] Compare shapes without
== on symbolic dims in the reshape shortcut
#20377
opened Sep 17, 2026 by
hiyufan
Contributor
Loading…
[Fix][Relax][Frontend][Torch] Make any and prod follow torch: missing overloads and result dtypes
#20376
opened Sep 17, 2026 by
hiyufan
Contributor
Loading…
[Relax][Frontend][Torch] Add amax, amin and min.dim converters
#20375
opened Sep 17, 2026 by
hiyufan
Contributor
Loading…
[Fix][Relax][Frontend][Torch] Accumulate integer cumsum and cumprod in int64
#20374
opened Sep 17, 2026 by
hiyufan
Contributor
Loading…
[Fix][Relax][Frontend][Torch] Follow torch's dtype rules for the division family
#20373
opened Sep 17, 2026 by
hiyufan
Contributor
Loading…
[Fix][Relax][Frontend][Torch] Promote the tensor, not the scalar, in binary ops with a Python scalar
#20372
opened Sep 17, 2026 by
hiyufan
Contributor
Loading…
[FIX][Relax] Validate DeviceMesh cardinality without overflow
#20346
opened Sep 15, 2026 by
ruiling-smartbear
Loading…
[FIX][Relax] Guard unknown tensor shapes in VMShapeLower
#20345
opened Sep 15, 2026 by
ruiling-smartbear
Loading…
[FIX][TIR] Conservatively analyze unsigned branch conditions
#20344
opened Sep 15, 2026 by
sepcnt
Loading…
[FIX][Relax] Preserve symbolic shape dependencies in FuseOps
#20333
opened Sep 13, 2026 by
Junius-Wynn
Contributor
Loading…
[Fix][Relax] Preserve out_dtype in matmul rewrite passes
#20331
opened Sep 13, 2026 by
tintin1942
Loading…
[DLight][CUDA] Fall back from unsupported GEMV spatial tiles
#20330
opened Sep 13, 2026 by
Nanmur
Contributor
Loading…
[Test] Restore shadowed duplicate test functions in relax/runtime tests
#20326
opened Sep 12, 2026 by
Anai-Guo
Contributor
Loading…
[Fix][Relax][Frontend][Torch] Validate
dim in the squeeze converter
#20322
opened Sep 11, 2026 by
siyiweigeHEW
Contributor
Loading…
[Topi] Support negative indices in topi.gather_nd
#20316
opened Sep 11, 2026 by
linsen458-spec
Loading…
Previous Next
ProTip!
Mix and match filters to narrow down what you’re looking for.