Add README.md

README.md

+vllm测试
+0.7.2
+Offline推理
+benchmark_throughput_0.7.2.py
+使用如下脚本可以减少不同参数推理时反复load模型
+batch prompt_tokens completion_tokens可以用空格分隔传成字符串
+其他参数与标准脚本一致
+bash
+export HIP_VISIBLE_DEVICES=1
+tp=1
+model_path=/llm-models/qwen1.5/Qwen1.5-0.5B-Chat
+
+batch="1 2"
+prompt_tokens="16 64"
+completion_tokens="128 256"
+python benchmark_throughput_0.7.2.py --model ${model_path} --tensor-parallel-size ${tp} --num-prompts ${batch} --input-len ${prompt_tokens} --output-len ${completion_tokens} \
+    --dtype float16  --trust-remote-code --max-model-len 32768 --output-json ./test_0.5B-0.7.2.txt
+
+按照如上传参，则计算的场景如下：
+bs    input    output
+1      16        128
+1      64        256
+2      16        128
+2      64        256
+
+推理结果汇总在--output-json ./test_0.5B-0.7.2.txt当中,示例如下表：
+
+bash
+bs_in_out,elapsed_time,Throughput,total_tokens,output_tokens,ttft_mean,ttft_median,ttft_p99,tpop_mean,tpop_median,tpop_p99,output_token_throughput_mean,output_token_throughput_median,output_token_throughput_p99,inout_token_throughput_mean,inout_token_throughput_median,inout_token_throughput_p99
+1_16_128,3.49,0.29,41.26,36.68,0.03801,0.03801,0.03801,0.0269,0.02691,0.02691,37.04,37.04,37.04,41.66,41.66,41.66
+1_64_256,7.14,0.14,44.82,35.85,0.0291,0.0291,0.0291,0.0278,0.02776,0.02776,36.01,36.01,36.01,45.01,45.01,45.01
+2_16_128,3.62,0.55,79.56,70.72,0.04829,0.04829,0.04893,0.028,0.02801,0.02801,35.51,35.51,35.51,39.94,39.94,39.95
+2_64_256,7.31,0.27,87.55,70.04,0.04697,0.04697,0.04764,0.0284,0.02836,0.02836,35.17,35.17,35.18,43.97,43.97,43.97
+
+Server推理
+benchmark_servein_0.7.2.py
+backend_request_func.py
+使用此方式可以避免sever推理时实际生成长度和指定长度不一致问题
+bash
+#使用提供的脚本进行测试
+
+#启动server
+vllm serve $MODEL_PATH  --trust-remote-code   --dtype $dtype --max-model-len $max_len -tp $tp  --gpu-memory-utilization 0.97
+
+
+
+#发送请求
+#--distributed-executor-backend ray等其他参数根据实际情况添加
+方式与平常一样，只是需要加上--ignore-eos
+python  benchmark_servein_0.7.2.py --backend vllm --ignore-eos  --dataset-name random --random-input-len  $input_len --random-output-len  $output_len --model $MODEL_PATH  --num-prompts $num_prompts --endpoint /v1/completions
+prof
+offline_prof
+hipprof
+prof.py
+benchmark_throughput_0.7.2_hipprof.py
+bash
+#使用示例：
+黄色背景为额外添加的部分
+SGLANG_PROF_ROCTX=1 hipprof --trace-off python benchmark_throughput_0.7.2_hipprof.py --num-prompts 1  --input-len 2000  --output-len 1 --model  /models/Llama-2-7b-hf  --trust-remote-code  --enforce-eager --dtype float16 > 7b-prefill-2000-test.log 2>&1 
+torchprof
+benchmark_throughput_0.7.2_torchprof.py
+bash
+#启动方式与平常使用一致
+benchmark_throughput_0.7.2_torchprof.py --num-prompts 1  --input-len 2000  --output-len 1 --model  /models/Llama-2-7b-hf  --trust-remote-code  --enforce-eager --dtype float16 > 7b-prefill-2000-test.log 2>&1
+
+会打印prof信息，保存的json文件名为:
+{args.num_prompts}-{args.input_len}-{args.output_len}-{args.tensor_parallel_size}_dcu.json
+
+server_prof
+worker.py
+bash
+替换/usr/local/lib/python3.10/site-packages/vllm/worker/worker.py
+
+#启动服务
+loca_path为保存的json文件绝对路径
+export VLLM_TORCH_PROFILER_DIR=$loca_path 
+vllm serve $MODEL_PATH  --trust-remote-code   --dtype $dtype --max-model-len $max_len -tp $tp  --gpu-memory-utilization 0.97
+
+#发送请求
+#--distributed-executor-backend ray等其他参数根据实际情况添加
+python  benchmark_servein_0.7.2.py --backend vllm --ignore-eos  --profile --dataset-name random --random-input-len  $input_len --random-output-len  $output_len --model $MODEL_PATH  --num-prompts $num_prompts --endpoint /v1/completions
+
+0.6.2
+Offline推理
+benchmark_throughput_0.6.2.py
+使用如下脚本可以减少不同参数推理时反复load模型
+batch prompt_tokens completion_tokens可以用空格分隔传成字符串
+其他参数与标准脚本一致
+bash
+export HIP_VISIBLE_DEVICES=1
+tp=1
+model_path=/llm-models/qwen1.5/Qwen1.5-0.5B-Chat
+
+
+batch="1 2"
+prompt_tokens="16 64"
+completion_tokens="128 256"
+python benchmark_throughput_0.6.2.py --model ${model_path} --tensor-parallel-size ${tp} --num-prompts ${batch} --input-len ${prompt_tokens} --output-len ${completion_tokens} \
+    --dtype float16  --trust-remote-code --max-model-len 32768 --output-json ./test_0.5B-0.6.2.txt
+
+按照如上传参，则计算的场景如下：
+bs    input    output
+1      16        128
+1      64        256
+2      16        128
+2      64        256
+
+推理结果汇总在--output-json ./test_0.5B-0.6.2.txt当中,示例如下表：
+
+bash
+bs_in_out,elapsed_time,Throughput,total_tokens,output_tokens,ttft_mean,ttft_median,ttft_p99,tpop_mean,tpop_median,tpop_p99,output_token_throughput_mean,output_token_throughput_median,output_token_throughput_p99,inout_token_throughput_mean,inout_token_throughput_median,inout_token_throughput_p99
+1_16_128,3.49,0.29,41.26,36.68,0.03801,0.03801,0.03801,0.0269,0.02691,0.02691,37.04,37.04,37.04,41.66,41.66,41.66
+1_64_256,7.14,0.14,44.82,35.85,0.0291,0.0291,0.0291,0.0278,0.02776,0.02776,36.01,36.01,36.01,45.01,45.01,45.01
+2_16_128,3.62,0.55,79.56,70.72,0.04829,0.04829,0.04893,0.028,0.02801,0.02801,35.51,35.51,35.51,39.94,39.94,39.95
+2_64_256,7.31,0.27,87.55,70.04,0.04697,0.04697,0.04764,0.0284,0.02836,0.02836,35.17,35.17,35.18,43.97,43.97,43.97
+
+Server推理
+benchmark_servein_0.6.2.py
+backend_request_func.py
+使用此方式可以减少server生成长度和指定长度差距过大
+Bash
+#使用提供的脚本进行测试
+
+#启动server
+vllm serve $MODEL_PATH  --trust-remote-code   --dtype $dtype --max-model-len $max_len -tp $tp  --gpu-memory-utilization 0.97
+
+
+
+#发送请求
+#--distributed-executor-backend ray等其他参数根据实际情况添加
+方式与平常一样，只是需要加上--ignore-eos
+python  benchmark_servein_0.6.2.py --backend vllm --ignore-eos  --dataset-name random --random-input-len  $input_len --random-output-len  $output_len --model $MODEL_PATH  --num-prompts $num_prompts --endpoint /v1/completions
+
+
+
+prof
+offline_porf
+hipprof
+prof.py
+benchmark_throughput_0.6.2_hipprof.py
+
+bash
+#使用示例：
+黄色背景为额外添加的部分
+SGLANG_PROF_ROCTX=1 hipprof --trace-off python benchmark_throughput_0.6.2_hipprof.py --num-prompts 1  --input-len 2000  --output-len 1 --model  /models/Llama-2-7b-hf  --trust-remote-code  --enforce-eager --dtype float16 > 7b-prefill-2000-test.log 2>&1 
+torchprof
+benchmark_throughput_0.6.2_torchprof.py
+bash
+#启动方式与平常使用一致
+benchmark_throughput_0.6.2_torchprof.py --num-prompts 1  --input-len 2000  --output-len 1 --model  /models/Llama-2-7b-hf  --trust-remote-code  --enforce-eager --dtype float16 > 7b-prefill-2000-test.log 2>&1
+
+会打印prof信息，保存的json文件名为:
+{args.num_prompts}-{args.input_len}-{args.output_len}-{args.tensor_parallel_size}_dcu.json
+server_prof
+worker.py
+bash
+替换/usr/local/lib/python3.10/site-packages/vllm/worker/worker.py
+
+#启动服务
+loca_path为保存的json文件绝对路径
+export VLLM_TORCH_PROFILER_DIR=$loca_path 
+vllm serve $MODEL_PATH  --trust-remote-code   --dtype $dtype --max-model-len $max_len -tp $tp  --gpu-memory-utilization 0.97
+
+#发送请求
+#--distributed-executor-backend ray等其他参数根据实际情况添加
+python  benchmark_servein_0.6.2.py --backend vllm --ignore-eos  --profile --dataset-name random --random-input-len  $input_len --random-output-len  $output_len --model $MODEL_PATH  --num-prompts $num_prompts --endpoint /v1/completions
+