MindWorkAI/AI-Studio
1
0 Fork 0
mirror of https://github.com/MindWorkAI/AI-Studio.git synced 2026-10-14 09:13:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add llmman as a self-hosted host for chat and embedding providers (#947)

Browse Source 
Co-authored-by: Thorsten Sommer <SommerEngineering@users.noreply.github.com>
This commit is contained in:
Eric CurtinandThorsten Sommer authored and GitHub committed 2026-10-13 13:52:43 +02:00
1 parent 2bd3d41421
commit 88d1f4d96a
20 files changed
+270 -89
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

app/MindWork AI Studio/Provider/Reasoning/ReasoningDispatcher.cs
+7
View File
@@ -125,6 +125,13 @@ public static class ReasoningDispatcher
Host.VLLM => [ReasoningDialect.OPEN_AI_COMPATIBLE, ReasoningDialect.REASONING_EFFORT, ReasoningDialect.QWEN_THINKING, ReasoningDialect.GOOGLE_THINKING, ReasoningDialect.VLLM],
//
// llmman starts llama.cpp for GGUF models and vLLM, SGLang, or MLX for the others, and
// hands their fields through unchanged. Which engine serves a model is up to llmman, so
// it is read in everything llama.cpp and vLLM are read in:
//
Host.LLMMAN => [ReasoningDialect.OPEN_AI_COMPATIBLE, ReasoningDialect.REASONING_EFFORT, ReasoningDialect.QWEN_THINKING, ReasoningDialect.GOOGLE_THINKING, ReasoningDialect.LLAMA_CPP, ReasoningDialect.VLLM],
_ => EVERYTHING_A_GATEWAY_MIGHT_SERVE,
},