-
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
[TIRx][CUDA] Replace source helpers with typed PTX forms
#20140
opened Aug 16, 2026 by
jinhongyii
Contributor
Loading…
[Fix][Relax] Preserve tensor-derived symbols during fusion
#20139
opened Aug 16, 2026 by
akaashrp
Contributor
Loading…
[Fix][Relax][Torch] Materialize runtime scalar shape values
#20138
opened Aug 16, 2026 by
akaashrp
Contributor
Loading…
[Fix][Relax][Torch] Align retained expand dimensions by trailing rank
#20137
opened Aug 16, 2026 by
akaashrp
Contributor
Loading…
[Feat][Web] Support per-parameter tensor cache encoding
#20136
opened Aug 16, 2026 by
akaashrp
Contributor
Loading…
[Fix][Relax] Preserve Torch integral power semantics
#20135
opened Aug 16, 2026 by
akaashrp
Contributor
Loading…
[Fix][Relax] Track lowered reshape storage aliases
#20134
opened Aug 16, 2026 by
akaashrp
Contributor
Loading…
[Fix][Relax] Lower non-contiguous WebGPU cumsum
#20133
opened Aug 16, 2026 by
akaashrp
Contributor
Loading…
[Fix][WebGPU] Validate and bound symbolic stack allocations
#20132
opened Aug 15, 2026 by
akaashrp
Contributor
Loading…
[BugFix] Align default (C) tirx.round lowering to ties-to-even
#20131
opened Aug 15, 2026 by
LngelKyo
Loading…
[Fix][TIRx] Preserve index semantics when narrowing to int32
#20129
opened Aug 13, 2026 by
akaashrp
Contributor
Loading…
[Fix][Relax][Torch] Preserve derived exported input dimensions
#20128
opened Aug 13, 2026 by
akaashrp
Contributor
Loading…
[Web] Avoid redundant memory byte copies
#20127
opened Aug 13, 2026 by
akaashrp
Contributor
Loading…
[Relax][ONNX] Support scalar QDQ inputs
#20126
opened Aug 12, 2026 by
Aharrypotter
Contributor
Loading…
[Fix][Relax][ONNX] Fold binary ops on symbolic PrimExpr scalars without numpy dispatch
#20123
opened Aug 12, 2026 by
Irfanuet191
Loading…
[Fix][DLight] Reject GEMV accesses unsupported by scheduling
#20122
opened Aug 12, 2026 by
akaashrp
Contributor
Loading…
[Fix][Relax][ONNX] Fold Min/Max/Sum/Mean constants elementwise
#20119
opened Aug 11, 2026 by
aryanputta
Loading…
[BugFix][TE] Initialize nested reductions at the outermost reduction scope
#20116
opened Aug 11, 2026 by
Gunse11er
Loading…
[Relax][Frontend][TFLite] Support StableHLO shape ops
#20114
opened Aug 11, 2026 by
Aharrypotter
Contributor
Loading…
fix: preserve LLVM vector value dominance across control flow
#20111
opened Aug 10, 2026 by
mvanhorn
Contributor
Loading…
[Relax][Frontend][ONNX] Support dynamic Range bounds
#20109
opened Aug 9, 2026 by
napronald
Contributor
Loading…
[Fix][TOPI] Fuse GPU scan blocks to avoid CUDA gridDim.y overflow
#20108
opened Aug 8, 2026 by
chenmiaoming
Loading…
[PageKVCache] Add support of sinks params and fix sliding windnow
#20104
opened Aug 7, 2026 by
krishnaraj36
Contributor
Loading…
Previous Next
ProTip!
What’s not been updated in a month: updated:<2026-07-16.