refactor: update llm model configurations and add AI agent guidelines

- Update nvim to use qwen3-coder-next-80b-instruct model
- Add AGENTS.md with AI agent best practices for timeout and file writing
- Update pi config to include agent guidelines
- Refactor llama-swap: remove old models, update quantizations, add tensor splits,
  remove GGML_CUDA_ENABLE_UNIFIED_MEMORY flags, and simplify configuration
This commit is contained in:
2026-02-06 21:28:31 -05:00
parent ec15ebb262
commit d685773604
4 changed files with 51 additions and 102 deletions

View File

@@ -1,10 +1,6 @@
local llm_endpoint = "https://llm-api.va.reichard.io"
local llm_assistant_model = "qwen3-coder-30b-instruct"
local llm_infill_model = "qwen3-coder-30b-instruct"
-- local llm_assistant_model = "devstral-small-2-instruct"
-- local llm_infill_model = "qwen2.5-coder-3b-instruct"
local llm_assistant_model = "qwen3-coder-next-80b-instruct"
local llm_infill_model = llm_assistant_model
local current_fim = "copilot" -- change this to switch default