llm: make load time stall duration configurable via OLLAMA_LOAD_TIMEOUT

With the new very large parameter models, some users are willing to wait for
a very long time for models to load.

cmd/cmd.go

@@ -1422,6 +1422,7 @@ func NewCLI() *cobra.Command {
 				envVars["OLLAMA_FLASH_ATTENTION"],
 				envVars["OLLAMA_LLM_LIBRARY"],
 				envVars["OLLAMA_GPU_OVERHEAD"],
+				envVars["OLLAMA_LOAD_TIMEOUT"],
 			})
 		default:
 			appendEnvDocs(cmd, envs)