File size: 1,834 Bytes
04ffcc8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 | CUDA_VISIBLE_DEVICES=1 vllm serve Elfsong/VLM_stage_2_iter_0003500 \
--tensor-parallel-size 1 \
--gpu-memory-utilization 0.25 \
--quantization bitsandbytes \
--max_model_len 4096 \
--port 9000 \
--served-model-name Local-Model-03500
CUDA_VISIBLE_DEVICES=1 vllm serve Elfsong/VLM_stage_2_iter_0004500 \
--tensor-parallel-size 1 \
--gpu-memory-utilization 0.25 \
--quantization bitsandbytes \
--max_model_len 4096 \
--port 9001 \
--served-model-name Local-Model-04500
CUDA_VISIBLE_DEVICES=1 vllm serve Elfsong/VLM_stage_2_iter_0005500 \
--tensor-parallel-size 1 \
--gpu-memory-utilization 0.25 \
--quantization bitsandbytes \
--max_model_len 4096 \
--port 9002 \
--served-model-name Local-Model-05500
CUDA_VISIBLE_DEVICES=3 vllm serve Elfsong/VLM_stage_2_iter_0006500 \
--tensor-parallel-size 1 \
--gpu-memory-utilization 0.25 \
--quantization bitsandbytes \
--max_model_len 4096 \
--port 9003 \
--served-model-name Local-Model-06500
CUDA_VISIBLE_DEVICES=3 vllm serve Elfsong/VLM_stage_2_iter_0007500 \
--tensor-parallel-size 1 \
--gpu-memory-utilization 0.25 \
--quantization bitsandbytes \
--max_model_len 4096 \
--port 9004 \
--served-model-name Local-Model-07500
CUDA_VISIBLE_DEVICES=1 vllm serve Elfsong/VLM_stage_3_iter_0001500 \
--tensor-parallel-size 1 \
--gpu-memory-utilization 0.3 \
--quantization bitsandbytes \
--seed 42 \
--max_model_len 4096 \
--port 9002 \
--served-model-name Local-Model-01500
CUDA_VISIBLE_DEVICES=2 vllm serve Elfsong/VLM_stage_3_iter_0002000 \
--tensor-parallel-size 1 \
--gpu-memory-utilization 0.3 \
--quantization bitsandbytes \
--seed 42 \
--max_model_len 4096 \
--port 9003 \
--served-model-name Local-Model-02000 |