Sync with Microsoft ONNX Runtime - 31052026#1114

Closed

ai-fw-intg wants to merge 14 commits into

ovep-developfrom

sync_msft_31052026

Commits on May 29, 2026

Address external path references in loaded models (#28709)
yuslepukhin
authored
Flash Attention style tiled computation for CPU GQA quantized KV cache (#28695)
tianleiwu
authored
Add `tools/python/compile_contributors.py` `--paths` option (#28710)

edgchen1
and
Copilot
authored
Update CUDA 12.8 to 13.0 in CI workflows (#28458)

Copilot
and
tianleiwu
authored
Add explicit CUDA version suffix to GPU release artifacts (#28691)

kpkbandi
and
Kusuma Padma Kavya Bandi
authored
CUDA Plugin EP: NHWC Cleanup & Hardening (#28612)
tianleiwu
authored
Introduce checks to prevent buffer overflow, add tests (#28713)
yuslepukhin
authored
Update microsoft_gsl from v4.0.0 to v4.2.1 (fixes C4875 deprecation) (#28527)

Copilot
and
tianleiwu
authored

Commits on May 30, 2026