9c31b5d622
- Model migration: gemma-4-E4B → qwen3.5-9b-vlm - Dashboard reorder: Usage Over Time + GPU Metrics to top - Router counter leak fix (gpu_decr in except handler) - VLM slot upgrade 1→2 - Redis stale key cleanup - Automated maintenance cron job - LiteLLM config update - GPU router config update - README update
26 lines
624 B
YAML
26 lines
624 B
YAML
model_list:
|
|
- model_name: qwen3.6-35B-A3B
|
|
litellm_params:
|
|
model: openai/qwen3.6-35B-A3B
|
|
api_base: http://192.168.68.15:8080/v1
|
|
api_key: "not-needed"
|
|
|
|
- model_name: qwen3.6-27B-code
|
|
litellm_params:
|
|
model: openai/qwen3.6-27B-code-text
|
|
api_base: http://192.168.68.8:8080/v1
|
|
api_key: "not-needed"
|
|
|
|
- model_name: qwen3.5-9b-vlm
|
|
litellm_params:
|
|
model: openai/qwen3.5-9b-vlm
|
|
api_base: http://192.168.68.110:8080/v1
|
|
api_key: "not-needed"
|
|
|
|
general_settings:
|
|
master_key: sk-syslog-local-master-key
|
|
|
|
litellm_settings:
|
|
drop_params: true
|
|
request_timeout: 120
|