roger/k3s-cluster
1
0
Fork 1
Code Issues Pull Requests 6 Actions Packages Projects Releases Wiki Activity

deploy deepseek v4

Browse Source
This commit is contained in:
Roger Oriol
2026-08-01 00:24:26 +02:00
parent 5fe0ee361a
commit b132aae09c
14 changed files with 610 additions and 411 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
platform-engineer/configmap.yaml
View File

@@ -9,18 +9,18 @@ data:
config.yaml: |
model:
provider: openai-api
default: qwen3.6-27b
default: deepseek-v4-flash-0731
base_url: "http://litellm-service.litellm:80/v1"
api_mode: chat_completions
auxiliary:
compression:
provider: openai-api
model: qwen3.6-35b-a3b # flash model for speed-sensitive auxiliary tasks
model: deepseek-v4-flash-0731 # in-cluster llama.cpp model (replaces the Qwen flash/dense pair)
base_url: "http://litellm-service.litellm:80/v1"
title_generation:
provider: openai-api
model: qwen3.6-35b-a3b # flash model for speed-sensitive auxiliary tasks
model: deepseek-v4-flash-0731 # in-cluster llama.cpp model (replaces the Qwen flash/dense pair)
base_url: "http://litellm-service.litellm:80/v1"
terminal: