PR #26002 Reduce Python and Nuget GPU package size

Reduce Python and Nuget GPU package size #26002

chilo-ms merged 10 commits into main from chi/remove_cuda_arch

remove the oldest CUDA arch

b17b0a2b

update

86f73d2e

snnn requested a review from

tianleiwu 104 days ago

revmoe older arch in Linux python whl, Linux nuget and windows nuget

4ae35511

tianleiwu commented on 2025-09-10

remove old GPU arch for windows nuget

c32103d8

remove old GPU arch for python wheel

69ddc16c

jywu-msft added release:1.23.0

reduce number of k support in beam search

64f7967d

revert beam_search_topk

bc3f01c6

remove FPA_INTB_GEMM for Linux python wheel

9b226b16

revert beam_search_topk

b28e74b8

chilo-ms changed the title ~~Remove old CUDA arch in CMAKE_CUDA_ARCHITECTURES to reduce package size~~ Reduce Python and Nuget GPU package size 97 days ago

tianleiwu dismissed these changes on 2025-09-17

Add back support for SM75 on Linux and disable FPA_INTB_GEMM

5aeb8745

chilo-ms dismissed their stale review via 5aeb8745 96 days ago

snnn approved these changes on 2025-09-18

tianleiwu approved these changes on 2025-09-18

chilo-ms merged fd35afb9 into main 95 days ago

chilo-ms deleted the chi/remove_cuda_arch branch 95 days ago

snnn removed release:1.23.0

Reviewers

tianleiwu

snnn

Assignees

No one assigned

Labels

None yet

Milestone

No milestone

onnxruntime Reduce Python and Nuget GPU package size #26002 Merged

Reduce Python and Nuget GPU package size #26002

onnxruntime
Reduce Python and Nuget GPU package size
#26002

Merged