Skip to content

[PERFORMANCE]: Fix critical performance issues in llm-guard plugin #1959

@araujof

Description

@araujof

Tasks:

  • Async Redis operations - Single biggest bottleneck
  • Parallelize scanner execution - 3-5x speedup potential
  • Offload ML inference to threads - Prevent event loop blocking
  • Fix pickle blocking - Use async for large objects

Metadata

Metadata

Assignees

Labels

MUSTP1: Non-negotiable, critical requirements without which the product is non-functional or unsafebugSomething isn't workingperformancePerformance related itemsplugins

Type

Projects

No projects

Relationships

None yet

Development

No branches or pull requests

Issue actions