Merge C24 LoRA adapters on demand for vLLM, with affinity

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ilker ManapandClaude Opus 5.5 committed 2026-10-05 01:15:12 +02:00
commit bd3eca4092
24 files changed
+1773 -35

No files matched your search

+6 -4
View File
@@ -277,10 +277,12 @@ func newAdaptersCmd(client func() *ctlClient) *cobra.Command {
Use: "adapters <model> [--add NAME=URL[@SCALE]] [--remove NAME]",
Short: "List, add or remove a model's LoRA adapters",
Long: "An adapter is asked for by its NAME as though it were a model, and is served\n" +
"by this model's replicas with it applied. URL is the adapter file, usually in\n" +
"the mirror; it must be a GGUF LoRA adapter for this model's architecture,\n" +
"which is checked before it is attached. Replicas load a changed set when\n" +
"restarted: llmgw ctl restart --model MODEL.",
"by this model's replicas with it applied. URL is the adapter, usually in the\n" +
"mirror. For llama.cpp it must be a GGUF LoRA adapter for this model's\n" +
"architecture, which is checked before it is attached; for vLLM it is a PEFT\n" +
"adapter directory (a mirror version ending in /) or a Hugging Face repository\n" +
"id, which vLLM checks when it loads it. SCALE applies on llama.cpp only.\n" +
"Replicas load a changed set when restarted: llmgw ctl restart --model MODEL.",
Args: cobra.ExactArgs(1),
RunE: func(cmd *cobra.Command, args []string) error {
name := args[0]