Sync with Microsoft ONNX Runtime - 26062026#1166

Open

ai-fw-intg wants to merge 7 commits into

ovep-developfrom

sync_msft_26062026

Commits on Jun 24, 2026

Relax CompileModel validation to accept zero-input OrtModel graphs (#28771)
adrastogi
authored
Clamp derived sequence lengths and KV-cache index in CUDA GroupQueryAttention (#29240)

jiafatom
and
Copilot
authored
Add flash attention for non-quantized CPU GroupQueryAttention (#28962)
tianleiwu
authored