File size: 273 Bytes
7134ce7 | 1 2 3 4 5 6 7 8 9 | # GME/GTE models or your checkpoints are also supported
# transformers/vllm/sglang supported
CUDA_VISIBLE_DEVICES=0 swift deploy \
--host 0.0.0.0 \
--port 8000 \
--task_type embedding \
--model Qwen/Qwen3-Embedding-0.6B \
--infer_backend sglang
|