proxy: add swap matrix with solver-based model swapping (#646)

Add a new swap matrix to supersede groups for running concurrent models.
The matrix uses a solver that picks the lowest cost evictions to make a
requested model available. This simple approach along with a very basic
DSL grammar can enable very complex swapping scenarios.

- add DSL parser for set expressions with & (AND), | (OR), (), +ref
- add MatrixConfig structs, validation, and topological sort for +ref
- add MatrixSolver with cost-minimizing swap decisions
- add Matrix runtime integrating solver with Process lifecycle
- integrate matrix into ProxyManager with if-branches at all endpoints
- update config.example.yaml and config-schema.json with matrix schema
- config enforces groups XOR matrix (cannot use both)

fixes #643
This commit is contained in:
Benson Wong
2026-04-14 21:55:30 -07:00
committed by GitHub
parent 40e39f7a86
commit 35193f82f1
13 changed files with 2080 additions and 186 deletions
+32 -13
View File
@@ -129,6 +129,12 @@ type Config struct {
Profiles map[string][]string `yaml:"profiles"`
Groups map[string]GroupConfig `yaml:"groups"` /* key is group ID */
// swap matrix: solver-based alternative to groups
Matrix *MatrixConfig `yaml:"matrix"`
// populated during validation when matrix is configured
ExpandedSets []ExpandedSet `yaml:"-"`
// for key/value replacements in model's cmd, cmdStop, proxy, checkEndPoint
Macros MacroList `yaml:"macros"`
@@ -438,22 +444,35 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
config.Models[modelId] = modelConfig
}
config = AddDefaultGroupToConfig(config)
// groups XOR matrix
if config.Matrix != nil && len(config.Groups) > 0 {
return Config{}, fmt.Errorf("config cannot use both 'groups' and 'matrix'")
}
// Validate group members
memberUsage := make(map[string]string)
for groupID, groupConfig := range config.Groups {
prevSet := make(map[string]bool)
for _, member := range groupConfig.Members {
if _, found := prevSet[member]; found {
return Config{}, fmt.Errorf("duplicate model member %s found in group: %s", member, groupID)
}
prevSet[member] = true
if config.Matrix != nil {
expandedSets, err := ValidateMatrix(*config.Matrix, config.Models)
if err != nil {
return Config{}, fmt.Errorf("matrix: %w", err)
}
config.ExpandedSets = expandedSets
} else {
config = AddDefaultGroupToConfig(config)
if existingGroup, exists := memberUsage[member]; exists {
return Config{}, fmt.Errorf("model member %s is used in multiple groups: %s and %s", member, existingGroup, groupID)
// Validate group members
memberUsage := make(map[string]string)
for groupID, groupConfig := range config.Groups {
prevSet := make(map[string]bool)
for _, member := range groupConfig.Members {
if _, found := prevSet[member]; found {
return Config{}, fmt.Errorf("duplicate model member %s found in group: %s", member, groupID)
}
prevSet[member] = true
if existingGroup, exists := memberUsage[member]; exists {
return Config{}, fmt.Errorf("model member %s is used in multiple groups: %s and %s", member, existingGroup, groupID)
}
memberUsage[member] = groupID
}
memberUsage[member] = groupID
}
}