serversdown/project-lyra
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: point MI50 backend at 10.0.0.42 (avoid terra-mechanics conflict)

Browse Source 
CT202's old static 10.0.0.44 collided with the terra-mechanics dev VM (tmi-dev).
Reassigned CT202 to 10.0.0.42 and repointed MI50_BASE_URL accordingly.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
serversdown
2026-06-16 05:52:15 +00:00
parent 30185f3fd8
commit aae95bfa6c
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.env.example
+2 -2
View File
@@ -2,8 +2,8 @@
LOCAL_BASE_URL=http://localhost:11434 LOCAL_BASE_URL=http://localhost:11434
LOCAL_MODEL=qwen2.5:7b-instruct LOCAL_MODEL=qwen2.5:7b-instruct
# MI50 backend — OpenAI-compatible llama.cpp server on the home-lab GPU box. # MI50 backend — OpenAI-compatible llama.cpp server on the home-lab GPU box (CT202).
MI50_BASE_URL=http://10.0.0.44:8080/v1 MI50_BASE_URL=http://10.0.0.42:8080/v1
MI50_MODEL=local-gpu MI50_MODEL=local-gpu
# Cloud backend (OpenAI) — higher quality, costs money. # Cloud backend (OpenAI) — higher quality, costs money.
lyra/config.py
+1 -1
View File
@@ -29,7 +29,7 @@ def load() -> Config:
return Config( return Config(
local_base_url=os.getenv("LOCAL_BASE_URL", "http://localhost:11434"), local_base_url=os.getenv("LOCAL_BASE_URL", "http://localhost:11434"),
local_model=os.getenv("LOCAL_MODEL", "qwen2.5:7b-instruct"), local_model=os.getenv("LOCAL_MODEL", "qwen2.5:7b-instruct"),
mi50_base_url=os.getenv("MI50_BASE_URL", "http://10.0.0.44:8080/v1"), mi50_base_url=os.getenv("MI50_BASE_URL", "http://10.0.0.42:8080/v1"),
mi50_model=os.getenv("MI50_MODEL", "local-gpu"), mi50_model=os.getenv("MI50_MODEL", "local-gpu"),
openai_api_key=os.getenv("OPENAI_API_KEY", ""), openai_api_key=os.getenv("OPENAI_API_KEY", ""),
cloud_model=os.getenv("CLOUD_MODEL", "gpt-4o-mini"), cloud_model=os.getenv("CLOUD_MODEL", "gpt-4o-mini"),