Upload README.md with huggingface_hub

README.md

@@ -90,7 +90,7 @@ export VLLM_PLUGINS=fl
 export TRITON_ALL_BLOCKS_PARALLEL=1
 export USE_FLAGGEMS=1
 export HIP_VISIBLE_DEVICES=2,3
-ulimit -n 2048 && nohup env   VLLM_USE_MODELSCOPE=true   VLLM_FL_FLAGOS_WHITELIST="arange_start,lt,where_self_out,argmax,zeros_like,bitwise_or_tensor,scatter,rsub_scalar,ones,cumsum,bitwise_and_tensor,resolve_neg,lt_scalar,sum_dim,add,diff,index,le,masked_fill,where_self,bitwise_not,gather,mul,zero_,nonzero,resolve_conj,cumsum_out,gt_scalar,softmax_out,softmax"   vllm serve   --model /data/DeepSeek-R1-Distill-Qwen-1.5B-hygon-FlagOS   --served-model-name DeepSeek-R1-Distill-Qwen-1.5B-hygon-FlagOS   --host 0.0.0.0   --port 8000   --gpu-memory-utilization 0.90   --trust-remote-code   --tensor-parallel-size 2   > DeepSeek-R1-Distill-Qwen-1.5B-hygon-FlagOS.log 2>&1 &
+ulimit -n 2048 && nohup env VLLM_FL_FLAGOS_WHITELIST="arange_start,lt,where_self_out,argmax,zeros_like,bitwise_or_tensor,scatter,rsub_scalar,ones,cumsum,bitwise_and_tensor,resolve_neg,lt_scalar,sum_dim,add,diff,index,le,masked_fill,where_self,bitwise_not,gather,mul,zero_,nonzero,resolve_conj,cumsum_out,gt_scalar,softmax_out,softmax"   vllm serve   --model /data/DeepSeek-R1-Distill-Qwen-1.5B-hygon-FlagOS   --served-model-name DeepSeek-R1-Distill-Qwen-1.5B-hygon-FlagOS   --host 0.0.0.0   --port 8000   --gpu-memory-utilization 0.90   --trust-remote-code   --tensor-parallel-size 2   > DeepSeek-R1-Distill-Qwen-1.5B-hygon-FlagOS.log 2>&1 &
 ```
 
 ## Service Invocation