update

Signed-off-by: 1092626063 <[email protected]>

Author: 1092626063

docs/source/tutorials/DeepSeek-V3.1.md

@@ -84,7 +84,7 @@ export OMP_PROC_BIND=false
 export OMP_NUM_THREADS=100
 export VLLM_USE_V1=1
 export HCCL_BUFFSIZE=200
-export VLLM_ASCEND_ENALBE_MLAPO=1
+export VLLM_ASCEND_ENABLE_MLAPO=1
 export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
 export VLLM_ASCEND_ENABLE_FLASHCOMM1=0
 export DISABLE_L2_CACHE=1
@@ -98,9 +98,9 @@ vllm serve vllm-ascend/DeepSeek-V3.1_w8a8mix_mtp \
 --seed 1024 \
 --served-model-name deepseek_v3 \
 --enable-expert-parallel \
---max-num-seqs 8 \
---max-model-len 40000 \
---max-num-batched-tokens 2048 \
+--max-num-seqs 16 \
+--max-model-len 8192 \
+--max-num-batched-tokens 4096 \
 --trust-remote-code \
 --no-enable-prefix-caching \
 --gpu-memory-utilization 0.92 \
@@ -144,9 +144,9 @@ export OMP_NUM_THREADS=100
 export VLLM_USE_V1=1
 export HCCL_BUFFSIZE=200
 export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
-export VLLM_ASCEND_ENALBE_MLAPO=1
-export HCCL_INTRA_PCIE_ENALBE=1
-export HCCL_INTRA_ROCE_ENALBE=0
+export VLLM_ASCEND_ENABLE_MLAPO=1
+export HCCL_INTRA_PCIE_ENABLE=1
+export HCCL_INTRA_ROCE_ENABLE=0
 
 vllm serve vllm-ascend/DeepSeek-V3.1_w8a8mix_mtp \
 --host 0.0.0.0 \
@@ -199,13 +199,14 @@ export OMP_PROC_BIND=false
 export OMP_NUM_THREADS=100
 export HCCL_BUFFSIZE=200
 export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
-export VLLM_ASCEND_ENALBE_MLAPO=1
-export HCCL_INTRA_PCIE_ENALBE=1
-export HCCL_INTRA_ROCE_ENALBE=0
+export VLLM_ASCEND_ENABLE_MLAPO=1
+export HCCL_INTRA_PCIE_ENABLE=1
+export HCCL_INTRA_ROCE_ENABLE=0
 
 vllm serve vllm-ascend/DeepSeek-V3.1_w8a8mix_mtp \
 --host 0.0.0.0 \
 --port 8004 \
+--headless \
 --data-parallel-size 4 \
 --data-parallel-size-local 2 \
 --data-parallel-start-rank 2 \
@@ -368,7 +369,7 @@ export HCCL_CONNECT_TIMEOUT=120
 export OMP_PROC_BIND=false
 export OMP_NUM_THREADS=10
 export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
-export VLLM_ASCEND_ENALBE_MLAPO=1
+export VLLM_ASCEND_ENABLE_MLAPO=1
 export HCCL_BUFFSIZE=256
 export TASK_QUEUE_ENABLE=1
 export HCCL_OP_EXPANSION_MODE="AIV"
@@ -449,7 +450,7 @@ export HCCL_CONNECT_TIMEOUT=120
 export OMP_PROC_BIND=false
 export OMP_NUM_THREADS=10
 export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
-export VLLM_ASCEND_ENALBE_MLAPO=1
+export VLLM_ASCEND_ENABLE_MLAPO=1
 export HCCL_BUFFSIZE=256
 export TASK_QUEUE_ENABLE=1
 export HCCL_OP_EXPANSION_MODE="AIV"
@@ -530,7 +531,7 @@ export HCCL_CONNECT_TIMEOUT=120
 export OMP_PROC_BIND=false
 export OMP_NUM_THREADS=10
 export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
-export VLLM_ASCEND_ENALBE_MLAPO=1
+export VLLM_ASCEND_ENABLE_MLAPO=1
 export HCCL_BUFFSIZE=600
 export TASK_QUEUE_ENABLE=1
 export HCCL_OP_EXPANSION_MODE="AIV"
@@ -611,7 +612,7 @@ export HCCL_CONNECT_TIMEOUT=120
 export OMP_PROC_BIND=false
 export OMP_NUM_THREADS=10
 export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
-export VLLM_ASCEND_ENALBE_MLAPO=1
+export VLLM_ASCEND_ENABLE_MLAPO=1
 export HCCL_BUFFSIZE=600
 export TASK_QUEUE_ENABLE=1
 export HCCL_OP_EXPANSION_MODE="AIV"