deploy: Dockerfile, Compose pro Rolle, LiteLLM, Prometheus/Alertmanager, Canary-Prober, n8n-Workflows
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,9 @@
|
||||
SLOT_ALIAS=tier1-general
|
||||
VLLM_MODEL=Qwen/Qwen3-14B-AWQ
|
||||
MAX_MODEL_LEN=32768
|
||||
GPU_MEM_UTIL=0.90
|
||||
MAX_LORAS=4
|
||||
MAX_LORA_RANK=64
|
||||
MODELS_DIR=/srv/models
|
||||
ADAPTERS_DIR=/srv/adapters
|
||||
HF_TOKEN=
|
||||
Reference in New Issue
Block a user