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

Sure, what exactly are you struggling with in there?

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

[Bild] 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. [Bild] Olajuwon: Tokenizer We have a few tokenizers to helps us limit …

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

Manuelle Konfiguration für VLLM

Unterstützung

Falco (Falco) 11. Oktober 2024 um 20:04 2

Sicher, womit genau haben Sie dort zu kämpfen?

Thema		Antworten	Aufrufe
Debugging adding new LLM Support ai	8	485	23. August 2024
Self-Hosting an OpenSource LLM for DiscourseAI Self-Hosting ai	12	3931	6. Juli 2026
创建可用的llm后也无法设置 AI default LLM model Support ai	3	65	20. März 2026
Discourse AI - Large Language Model (LLM) settings page Site Management how-to , ai	20	3899	9. Mai 2026
Adding Semantic Search feature for our self-hosted discourse site Support ai , ai-search	9	329	19. März 2025

Manuelle Konfiguration für VLLM

Verwandte Themen