etp best a2 (#1101)

### What this PR does / why we need it?
Single machine 16 cards deepseekr1 attention (tp8/dp2) / moe(etp) Best
performance

rely on:
vllm-ascend commit id:da9acfca6053352730fce75fb772e214755d0341
vllm commit id:b124e1085b1bf977e3dac96d99ffd9d8ddfdb6cc
+ #910 + [Reduce
_npu_flash_attention mask to 128x128 for memory savings]
#1100 [Reduce memory
usage by splitting tokens in fused_experts]


---------

Signed-off-by: ttanzhiqiang <389825161@qq.com>

Author: ttanzhiqiang

examples/run_dp_attention_etp16.sh

@@ -0,0 +1,23 @@
+export VLLM_ENABLE_MC2=0
+export VLLM_USE_V1=1
+export TASK_QUEUE_ENABLE=1
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+export ASCEND_LAUNCH_BLOCKING=0
+export VLLM_VERSION=0.9.0
+
+nohup python -m vllm.entrypoints.openai.api_server --model=/mnt/deepseek/DeepSeek-R1-W8A8-VLLM \
+    --quantization ascend \
+    --trust-remote-code \
+    --distributed-executor-backend=mp \
+    --port 8006 \
+    -tp=8 \
+    -dp=2 \
+    --max-num-seqs 24 \
+    --max-model-len 32768 \
+    --max-num-batched-tokens 32768 \
+    --block-size 128 \
+    --no-enable-prefix-caching \
+    --additional-config '{"torchair_graph_config":{"enabled":true,"use_cached_graph":true,"graph_batch_sizes":[24]},"ascend_scheduler_config":{"enabled":true},"expert_tensor_parallel_size":16}' \
+    --gpu-memory-utilization 0.96 &> run.log &
+disown

examples/run_dp_attention_etp16_benmark.sh

@@ -0,0 +1,56 @@
+#!/bin/bash
+# Concurrency array
+concurrency_array=(48)
+#best rate
+rate_array=(0.7)
+
+# Result file
+result_file="benchmark_results.txt"
+echo "Benchmark Results" > $result_file
+echo "===================" >> $result_file
+
+# Loop through all combinations
+for concurrency in "${concurrency_array[@]}"; do
+    for rate in "${rate_array[@]}"; do
+        echo "Testing with concurrency=$concurrency, rate=$rate"
+        echo "" >> $result_file
+        echo "Concurrency: $concurrency, Request Rate: $rate" >> $result_file
+        echo "-------------------" >> $result_file
+
+        # Run benchmark test
+        python /mnt/deepseek/vllm/benchmarks/benchmark_serving.py \
+            --backend vllm \
+            --trust-remote-code \
+            --model /mnt/deepseek/DeepSeek-R1-W8A8-VLLM \
+            --dataset-name random \
+            --random-input-len 4096 \
+            --random-output-len 1536 \
+            --ignore-eos \
+            --num-prompts 400 \
+            --max-concurrency $concurrency \
+            --request-rate $rate \
+            --metric-percentiles 90 \
+            --base-url http://localhost:8006 2>&1 | tee -a $result_file
+
+        # Wait for system cool down
+        sleep 30
+    done
+done
+
+# Analyze results
+echo "Analysis Results" > analysis_results.txt
+echo "=================" >> analysis_results.txt
+
+# Extract and analyze TPOT data
+echo "TPOT Analysis:" >> analysis_results.txt
+grep "Mean TPOT" $result_file | awk -F':' '{
+    printf "Concurrency %s, Rate %s: %s ms\n", $1, $2, $3
+}' >> analysis_results.txt
+
+# Extract and analyze throughput data
+echo -e "\nThroughput Analysis:" >> analysis_results.txt
+grep "Output token throughput" $result_file | awk -F':' '{
+    printf "Concurrency %s, Rate %s: %s tokens/s\n", $1, $2, $3
+}' >> analysis_results.txt
+
+echo "Testing completed. Results saved in $result_file and analysis in analysis_results.txt"