Skip to content

[CPU] Add FP32 GEMV decode kernel for GroupQueryAttention#29216

Merged
tianleiwu merged 3 commits into
mainfrom
tlwu/20260608/gqa_cpu_decode_gemv
Jun 26, 2026
Merged

[CPU] Add FP32 GEMV decode kernel for GroupQueryAttention#29216
tianleiwu merged 3 commits into
mainfrom
tlwu/20260608/gqa_cpu_decode_gemv

Fix non-deterministic FP32 GQA decode for ragged seqlens; add parity …

bb024f2
Select commit
Loading
Failed to load commit list.
Azure Pipelines / Linux Android Emulator QNN CI Pipeline succeeded Jun 25, 2026 in 13m 53s

Build #20260624.74 succeeded

0 errors / 0 warnings

View more details on Azure Pipelines