eval

package
v1.2.10 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: Mar 23, 2026 License: MIT Imports: 7 Imported by: 0

Documentation

Overview

Package eval runs the DAG-Math memory evaluation experiment. Two modes (set via EXPERIMENT_MODE):

  • flush_per_request: every stage gets CachePolicy="flush", so KV cache is evicted after each LLM call
  • flush_per_workflow: default Orla policy (preserve across stages, flush at workflow boundary)

Index

Constants

View Source 
const (
	ModeFlushPerRequest  = "flush_per_request"
	ModeFlushPerWorkflow = "flush_per_workflow"
)

Variables

This section is empty.

Functions

func Run 

func Run(ctx context.Context, dataset *shared.DAGMathDataset, mode string) error

Types

This section is empty.

Source Files

View all Source files

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.