96 replies

LLM request timed out. When setting up VLLM

I have openclaw running on my mac mini trying to use VLLM on my worksation on my network, I can curl the model fine from the mac, but when I try and use my discord bot or even the chat in the portal, it's throwing a LLM timeout, it's not hitting the workstation endpoint.

  "models": {
    "mode": "merge",
    "providers": {
      "vllm": {
        "baseUrl": "http://192.168.1.80:8000/v1",

  "models": {
    "mode": "merge",
    "providers": {
      "vllm": {
        "baseUrl": "http://192.168.1.80:8000/v1",

LLM request timed out. When setting up VLLM

Similar Threads

LLM request timed out. When setting up VLLM

Similar Threads

Similar Threads

Similar Threads