x
This commit is contained in:
@@ -3,6 +3,8 @@ MODEL_KEY=Qwen3.5-35B-A3B-GPTQ-Int4
|
||||
MODEL_NAME=
|
||||
HOST=0.0.0.0
|
||||
PORT=8000
|
||||
OPENAI_HOST=0.0.0.0
|
||||
OPENAI_PORT=8001
|
||||
TENSOR_PARALLEL_SIZE=2
|
||||
GPU_MEMORY_UTILIZATION=0.92
|
||||
MAX_MODEL_LEN=8192
|
||||
|
||||
Reference in New Issue
Block a user