Skip to content

perf: avoid scanning KV cache pages for capacity checks - #576

Open
T4t4KAU wants to merge 1 commit into
InfiniTensor:InfiniLM-v0.2.9cfrom
T4t4KAU:perf/kv-cache-capacity-index
Open

T4t4KAU wants to merge 1 commit into
InfiniTensor:InfiniLM-v0.2.9cfrom
T4t4KAU:perf/kv-cache-capacity-index

perf: avoid scanning KV cache pages for capacity checks

21c1444
Select commit
Loading
Failed to load commit list.

Workflow runs completed with no jobs