Initial production-ready Gemma 3 vLLM ROCm stack
Co-Authored-By: Oz <oz-agent@warp.dev>
This commit is contained in:
9
.env.example
Normal file
9
.env.example
Normal file
@ -0,0 +1,9 @@
|
||||
HF_TOKEN=YOUR_HF_TOKEN_HERE
|
||||
VLLM_API_KEY=YOUR_LOCAL_API_KEY_HERE
|
||||
GEMMA_MODEL_ID=google/gemma-3-1b-it
|
||||
BACKEND_PORT=8000
|
||||
FRONTEND_PORT=3000
|
||||
HUGGINGFACE_CACHE_DIR=/home/${USER}/.cache/huggingface
|
||||
OPEN_WEBUI_DATA_DIR=./frontend/data/open-webui
|
||||
VLLM_MAX_MODEL_LEN=4096
|
||||
VLLM_GPU_MEMORY_UTILIZATION=0.88
|
||||
Reference in New Issue
Block a user