-
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][DLight] Localize private scalar reduction buffers
#20160
opened Aug 19, 2026 by
SamJSui
Contributor
Loading…
[TIRx][CUDA] Add register and cluster launch controls
#20159
opened Aug 19, 2026 by
spectrometerHBH
Contributor
Loading…
[Fix][Relax][Frontend][ONNX] Support Pad mode="wrap" and axes input for op…
#20152
opened Aug 17, 2026 by
siyiweigeHEW
Loading…
[Fix][Relax][Frontend][ONNX] Support broadcastable multi-axis PRelu slopes
#20149
opened Aug 17, 2026 by
siyiweigeHEW
Loading…
[Fix][Relax][Frontend][ONNX] Fix Mean/Sum/Min/Max with all-constant inputs
#20147
opened Aug 17, 2026 by
siyiweigeHEW
Loading…
[Fix][Relax][Frontend][ONNX] Validate Flatten axis range in
from_onnx
#20145
opened Aug 17, 2026 by
siyiweigeHEW
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] Lower non-contiguous WebGPU cumsum
#20133
opened Aug 16, 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…
[Fix][Relax][ONNX] Fold binary ops on symbolic PrimExpr scalars without numpy dispatch
#20123
opened Aug 12, 2026 by
Irfanuet191
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…
Bump cryptography from 41.0.6 to 50.0.0 in /docker/python
dependencies
Pull requests that update a dependency file
python
Pull requests that update Python code
#20087
opened Aug 4, 2026 by
dependabot
Bot
Loading…
[Relax][cuDNN] Do not offload causal / non-fp16 attention, and fix the default softmax scale
#20078
opened Jul 30, 2026 by
YangXu1990uiuc
Loading…
[Runtime][Disco][Relax] Add CPUCCL support for distributed execution
#20077
opened Jul 30, 2026 by
Laiyyi
Loading…
Previous Next
ProTip!
no:milestone will show everything without a milestone.