Fix int32 overflow in CUDA Cast and UnaryElementWise kernels for tensors with >2^31 elements #28386
Initial plan
3ace5f31
Fix int32 overflow in CUDA Cast and UnaryElementWise kernels for tens…
5f5b2362
Fix placeholder issue number in test comment
92ac4fa6
copilot-swe-agent
changed the title [WIP] Fix CUDA Cast kernel illegal memory access on large tensors Fix int32 overflow in CUDA Cast and UnaryElementWise kernels for tensors with >2^31 elements 187 days ago
Address review feedback: use size_t for pair_count, rename test, add …
f28a737e
Merge remote-tracking branch 'origin/main' into copilot/fix-cuda-cast…
081aa2fa
check blocksPerGrid
ad13c0ef
tianleiwu
marked this pull request as ready for review 175 days ago
tianleiwu
merged
cd05ef40
into main 174 days ago
tianleiwu
deleted the copilot/fix-cuda-cast-kernel-crash branch 174 days ago
Login to write a write a comment.
Login via GitHub