Please, I need help with the manual configuration of VLLM in the AI model section admin/plugins/discourse-ai/ai-llms/new?llmTemplate=none.

I’m unsure about these two options and how to utilize them, specifically in relation to the API. URL of the service hosting the model Tokenizer

[image] Olajuwon: URL of the service hosting the model That is the hostname of the machine where you are running vLLM. It may also work with an IP in the form of http://1.1.1.1:1111 but I have not tested it as such. [image] Olajuwon: Tokenizer We have a few tokenizers to helps us limi…

OMG, this is too complex for me atm, would go with Sambanova Instead!

Manual configuration For VLLM

Support

Falco (Falco) October 11, 2024, 8:04pm 2

Sure, what exactly are you struggling with in there?

Topic		Replies	Views
Debugging adding new LLM Support ai	8	384	August 23, 2024
Self-Hosting an OpenSource LLM for DiscourseAI Self-Hosting ai	7	3587	January 20, 2026
Discourse AI - Large Language Model (LLM) settings page Site Management ai , how-to	20	3219	November 26, 2025
创建可用的llm后也无法设置 AI default LLM model Support ai	3	34	March 20, 2026
Adding Semantic Search feature for our self-hosted discourse site Support ai , ai-search	9	253	March 19, 2025

Manual configuration For VLLM

Related topics