onnxruntime
use correct total length to fix static kv_cache performance
#23615
Merged
Merged
use correct total length to fix static kv_cache performance #23615
guschmue
merged
1 commit into
main
from
gs/gqa-static-kv-cache
use correct total length to fix static kv_cache performance
0a0a5ca7
satyajandhyala
approved these changes
on 2025-02-11
Login to write a write a comment.
Login via GitHub