Files
inference-harness/litellm_config.yaml
T
Abiba Bot dace488f93 VLM migration: qwen3.5-9b-vlm → gemma-4-12b across entire harness
- router/router.py: model ID, context window (131K→262K), VRAM comment
- litellm_config.yaml: model name updated
- gpu-router.conf, gpu-router-docker.conf: pool names, comments
- dashboard/dashboard.py: MODELS array refactor for single-point config
- README.md: architecture diagram, model table
2026-06-05 21:37:18 +00:00

26 lines
618 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: gemma-4-12b
litellm_params:
model: openai/gemma-4-12b
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