Skip to content
CodeQL

Layer-wise KV Cache Allocation for Models with Alternating Attention Patterns #6288

Sign in to view logs

Layer-wise KV Cache Allocation for Models with Alternating Attention Patterns

Layer-wise KV Cache Allocation for Models with Alternating Attention Patterns #6288

Triggered via pull request October 22, 2025 08:14
@anujjanujj
synchronize #1832
anujj:gemma_interleaved_kv
Status Success
Total duration 1m 28s
Artifacts –

codeql.yml

on: pull_request
Matrix: Analyze
Fit to window
Zoom out
Zoom in