Files
llmgw/internal/control/catalog/environments.go
T
Ilker ManapandClaude Opus 5.5 aa531b1053 ComfyUI models of one environment share one replica
flux and sf3d on one card handed it to each other, each starting ComfyUI
and loading its weights from nothing (BACKLOG H3, placement side). An
environment of two or more models now gets a hidden catalog entry,
comfyui-env-<name>: on its first member's profiles with the most memory
any member needs, on demand for the longest idle timeout, carrying every
member's weights, repositories and the environment's custom nodes. The
members get no replicas of their own; asking for one wants the entry.

The agent fetches each member's weights; the gate links all of them,
refusing two weights files of one name, links each member's Hugging Face
repository, and answers /v1/models for every member. The control plane
offers the replica under the members' names with each one's workflow and
checkpoint, which the router sends by the model asked for. A member's
sibling never evicts the replica serving it, and the members' load counts
as the entry's.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-14 13:55:34 +02:00

173 lines
5.9 KiB
Go

package catalog
import (
"fmt"
"regexp"
"slices"
"strings"
)
// Environments: the ComfyUI models that may share one replica.
//
// Every ComfyUI model used to run in a replica of its own, so two models on
// one card took turns with a cold start each time: flux, then a mesh model,
// then flux again, each loading ComfyUI and its weights from nothing. ComfyUI
// itself moves between models' weights in one process; what keeps two models
// out of one process is their custom nodes, which share one Python. An
// environment is a set of models whose nodes can: the catalog checks it, and
// placement may then run one replica for all of them.
// Environment is one environment's models and what a replica of it carries.
type Environment struct {
Name string `json:"name"`
// Models are the catalog models in it, in catalog order.
Models []string `json:"models"`
// Nodes are every custom node any of them names, once each.
Nodes []CustomNode `json:"nodes,omitempty"`
// Sources are every weights source its models load, once each: what a
// replica of it must have on its node.
Sources []string `json:"sources,omitempty"`
}
// ComfyEnvironment is the environment a ComfyUI model is in, or "" for one in
// none, which is an environment of its own.
func (m Model) ComfyEnvironment() string {
if m.ComfyUI == nil {
return ""
}
return m.ComfyUI.Environment
}
var envName = regexp.MustCompile(`^[a-z0-9][a-z0-9._-]{0,62}$`)
// Environments are the catalog's named environments, by name.
func (c *Catalog) Environments() []Environment {
envs, _ := c.environments()
return envs
}
// EnvironmentOf is the environment a model is in, when it is in a named one.
func (c *Catalog) EnvironmentOf(model string) (Environment, bool) {
m, ok := c.Resolve(model)
if !ok || m.ComfyEnvironment() == "" {
return Environment{}, false
}
for _, e := range c.Environments() {
if e.Name == m.ComfyEnvironment() {
return e, true
}
}
return Environment{}, false
}
// environments builds the named environments and refuses one whose models
// cannot share a replica: two commits of one node, or two ranges of one
// package, of which one Python can hold only one.
func (c *Catalog) environments() ([]Environment, error) {
byName := map[string]*Environment{}
var order []string
// Who brought each node and each package into each environment, to name
// both models when two disagree.
nodeFrom := map[string]map[string]string{} // env -> repo -> model
nodeAt := map[string]map[string]string{} // env -> repo -> commit
pkgFrom := map[string]map[string]string{} // env -> package -> model
pkgSpec := map[string]map[string]string{} // env -> package -> spec
for _, name := range c.order {
m := c.models[name]
env := m.ComfyEnvironment()
if env == "" || m.IsEnvironment() {
continue
}
if !envName.MatchString(env) {
return nil, fmt.Errorf("model %q: comfyui.environment %q is not a name of lowercase letters, digits, '.', '_' and '-'",
name, env)
}
if !m.ServesComfyUI() || m.External != nil {
return nil, fmt.Errorf("model %q: comfyui.environment is for a model the cluster's ComfyUI serves", name)
}
e := byName[env]
if e == nil {
e = &Environment{Name: env}
byName[env] = e
order = append(order, env)
nodeFrom[env], nodeAt[env] = map[string]string{}, map[string]string{}
pkgFrom[env], pkgSpec[env] = map[string]string{}, map[string]string{}
}
e.Models = append(e.Models, name)
for _, src := range m.WeightSources() {
if !slices.Contains(e.Sources, src) {
e.Sources = append(e.Sources, src)
}
}
for _, n := range m.ComfyUI.Nodes {
repo := strings.TrimSuffix(strings.TrimRight(n.Repo, "/"), ".git")
if at, seen := nodeAt[env][repo]; seen {
if at != n.Commit {
return nil, fmt.Errorf("environment %q: models %q and %q name custom node %s at different commits (%s, %s): "+
"one replica holds one of them", env, nodeFrom[env][repo], name, n.Repo, short(at), short(n.Commit))
}
} else {
nodeAt[env][repo], nodeFrom[env][repo] = n.Commit, name
e.Nodes = append(e.Nodes, CustomNode{Repo: n.Repo, Commit: n.Commit})
}
i := slices.IndexFunc(e.Nodes, func(x CustomNode) bool {
return strings.TrimSuffix(strings.TrimRight(x.Repo, "/"), ".git") == repo
})
for _, b := range n.Build {
if !slices.Contains(e.Nodes[i].Build, b) {
e.Nodes[i].Build = append(e.Nodes[i].Build, b)
}
}
for _, r := range n.Requirements {
pkg, spec := requirementName(r), normalizeSpec(r)
if prev, seen := pkgSpec[env][pkg]; seen {
if prev != spec {
return nil, fmt.Errorf("environment %q: models %q and %q ask for %s as %q and %q: "+
"one Python holds one version; name the same range in both",
env, pkgFrom[env][pkg], name, pkg, prev, spec)
}
continue
}
pkgSpec[env][pkg], pkgFrom[env][pkg] = spec, name
// The requirement goes with the node that first named it:
// what the replica installs is the union, and each once.
e.Nodes[i].Requirements = append(e.Nodes[i].Requirements, strings.TrimSpace(r))
}
}
}
out := make([]Environment, 0, len(order))
for _, n := range order {
out = append(out, *byName[n])
}
return out, nil
}
// requirementName is a requirement's package, as PyPI compares names.
func requirementName(spec string) string {
s := strings.TrimSpace(spec)
if i := strings.IndexAny(s, "<>=!~;[ "); i >= 0 {
s = s[:i]
}
return strings.NewReplacer("_", "-", ".", "-").Replace(strings.ToLower(s))
}
// normalizeSpec is a requirement without its spaces and with its package
// named as PyPI compares it, so "transformers >=4.50, <5" and
// "Transformers>=4.50,<5" are one range.
func normalizeSpec(spec string) string {
s := strings.Join(strings.Fields(spec), "")
name := requirementName(s)
i := strings.IndexAny(s, "<>=!~;[")
if i < 0 {
return name
}
return name + s[i:]
}
func short(commit string) string {
if len(commit) > 12 {
return commit[:12]
}
return commit
}