minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[NPU] Update DeepSeek-V3.2 model deployment instructions in documentation (#21468)

Browse Source 
Co-authored-by: wuxue (C) <w00964934@china.huawei.com>
This commit is contained in:
Michelle Wu
2026-03-30 15:51:42 +08:00
committed by GitHub
co-authored by wuxue
parent b9a68c304e
commit 965f03cdc2
1 changed files with 98 additions and 150 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/platforms/ascend/ascend_npu_best_practice.md
+98 -150
View File
@@ -13,7 +13,7 @@ you encounter issues or have any questions, please [open an issue](https://githu
| Deepseek-R1 | Atlas 800I A3 | 32 | PD Separation | 3.9K+1K | 20ms | W8A8 INT8 | [Optimal Configuration](#deepseek-r1-3_9k-1k-20ms-on-a3-32-cards-separation-mode) |
| Deepseek-R1 | Atlas 800I A3 | 32 | PD Separation | 3.5K+1.5K | 20ms | W8A8 INT8 | [Optimal Configuration](#deepseek-r1-3_5k-1_5k-20ms-on-a3-32-cards-separation-mode) |
| Deepseek-R1 | Atlas 800I A3 | 32 | PD Separation | 3.5K+1K | 20ms | W8A8 INT8 | [Optimal Configuration](#deepseek-r1-3_5k-1k-20ms-on-a3-32-cards-separation-mode) |
| DeepSeek-V3.2-Exp | Atlas 800I A3 | 32 | PD Separation | 64K+3K | 30ms | W8A8 INT8 | [Optimal Configuration](#deepseek-v32-exp-64k-3k-30ms-on-a3-32-cards-separation-mode) |
| DeepSeek-V3.2 | Atlas 800I A3 | 32 | PD Separation | 128K+1K | 20ms | W8A8 INT8 | [Optimal Configuration](#deepseek-v32-128k-1k-20ms-on-a3-32-cards-separation-mode) |
### High Throughput
@@ -779,9 +779,9 @@ We tested it based on the `RANDOM` dataset.
python -m sglang.bench_serving --dataset-name random --backend sglang --host 127.0.0.1 --port 6688 --max-concurrency 384 --random-input-len 3500 --random-output-len 1500 --num-prompts 1536 --random-range-ratio 1
```
### DeepSeek-V3.2-Exp 64K-3K 30ms on A3 32 Cards Separation Mode
### DeepSeek-V3.2 128K-1K 20ms on A3 32 Cards Separation Mode
Model: DeepSeek-V3.2-Exp-W8A8
Model: DeepSeek-V3.2-W8A8
Hardware: Atlas 800I A3 32Card
@@ -789,14 +789,12 @@ DeployMode: PD Separation
Dataset: random
Input Output Length: 64K+3K
Input Output Length: 128K+1K
TPOT: 30ms
TPOT: 20ms
#### Model Deployment
Deploy Prefill Instance
```shell
echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
sysctl -w vm.swappiness=0
@@ -815,167 +813,117 @@ source /usr/local/Ascend/nnal/atb/set_env.sh
export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/opp/vendors/customize/op_api/lib/:${LD_LIBRARY_PATH}
export PATH=/usr/local/Ascend/8.5.0/compiler/bishengir/bin:$PATH
export ASCEND_HOME_PATH=/usr/local/Ascend/ascend-toolkit/latest
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export STREAMS_PER_DEVICE=32
export ASCEND_MF_STORE_URL="tcp://your prefill ip1:24670"
export HCCL_BUFFSIZE=1024
export DEEPEP_NORMAL_LONG_SEQ_ROUND=5
export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=512
P_IP=('your prefill ip1' 'your prefill ip2')
D_IP=('your decode ip1' 'your decode ip2')
MODEL_PATH=xxx
export SGLANG_NPU_USE_MLAPO=1
export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
export SGLANG_NPU_USE_MULTI_STREAM=1
export HCCL_OP_EXPANSION_MODE=AIV
LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
echo "${LOCAL_HOST1}"
echo "${LOCAL_HOST2}"
IPs=('your prefill ip1' 'your prefill ip2')
# get IP in current node
LOCAL_HOST=`hostname -I|awk -F " " '{print$1}'`
echo "LOCAL_HOST = " ${LOCAL_HOST}
# get node index
for i in "${!IPs[@]}";
# prefill
for i in "${!P_IP[@]}";
do
echo "LOCAL_HOST=${LOCAL_HOST}, IPs[${i}]=${IPs[$i]}"
if [ "$LOCAL_HOST" == "${IPs[$i]}" ]; then
echo "Node Rank : ${i}"
VC_TASK_INDEX=$i
break
fi
if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
then
echo "${P_IP[$i]}"
export HCCL_BUFFSIZE=1200
export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
export TASK_QUEUE_ENABLE=2
export HCCL_SOCKET_IFNAME=xxx
export GLOO_SOCKET_IFNAME=xxx
python3 -m sglang.launch_server --model-path ${MODEL_PATH} \
--tp 32 \
--trust-remote-code \
--attention-backend ascend \
--device npu \
--watchdog-timeout 9000 \
--host ${P_IP[$i]} --port 8000 \
--mem-fraction-static 0.73 \
--disable-radix-cache --chunked-prefill-size -1 --max-prefill-tokens 68000 \
--max-running-requests 1 \
--moe-a2a-backend deepep --deepep-mode normal \
--quantization modelslim \
--disaggregation-transfer-backend ascend \
--disaggregation-mode prefill \
--disable-cuda-graph \
--nnodes 2 --node-rank $i \
--disaggregation-bootstrap-port 8995 \
--moe-dense-tp-size 1 \
--enable-nsa-prefill-context-parallel \
--nsa-prefill-cp-mode in-seq-split \
--attn-cp-size 32 \
--speculative-algorithm NEXTN --speculative-num-steps 1 --speculative-eagle-topk 1 --speculative-num-draft-tokens 2 \
--dist-init-addr ${P_IP[0]}:10000
break
fi
done
IFNAMES=('xxx' 'xxx')
export HCCL_SOCKET_IFNAME=${IFNAMES[$VC_TASK_INDEX]}
export GLOO_SOCKET_IFNAME=${HCCL_SOCKET_IFNAME}
echo "HCCL_SOCKET_IFNAME : ${HCCL_SOCKET_IFNAME}"
nnodes=${#IPs[@]}
tp_size=`expr 16 \* ${nnodes}`
export ASCEND_MF_STORE_URL=tcp://${IPs[0]}:24667
python3 -m sglang.launch_server --model-path ${MODEL_PATH} \
--tp $tp_size \
--trust-remote-code \
--attention-backend ascend \
--device npu \
--watchdog-timeout 9000 \
--host ${IPs[$VC_TASK_INDEX]} --port 8000 \
--mem-fraction-static 0.73 \
--disable-radix-cache --chunked-prefill-size -1 --max-prefill-tokens 68000 \
--max-running-requests 1 \
--moe-a2a-backend deepep --deepep-mode normal \
--quantization modelslim \
--disaggregation-transfer-backend ascend \
--disaggregation-mode prefill \
--disable-cuda-graph \
--nnodes $nnodes --node-rank $VC_TASK_INDEX \
--disaggregation-bootstrap-port 8995 \
--enable-nsa-prefill-context-parallel --moe-dense-tp-size 1 \
--speculative-algorithm NEXTN --speculative-num-steps 1 --speculative-eagle-topk 1 --speculative-num-draft-tokens 2 \
--dist-init-addr ${IPs[0]}:10000
```
Deploy Decode Instance
```shell
echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
sysctl -w vm.swappiness=0
sysctl -w kernel.numa_balancing=0
sysctl -w kernel.sched_migration_cost_ns=50000
export SGLANG_SET_CPU_AFFINITY=1
unset https_proxy
unset http_proxy
unset HTTPS_PROXY
unset HTTP_PROXY
unset ASCEND_LAUNCH_BLOCKING
source /usr/local/Ascend/ascend-toolkit/set_env.sh
source /usr/local/Ascend/nnal/atb/set_env.sh
export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/opp/vendors/customize/op_api/lib/:${LD_LIBRARY_PATH}
export PATH=/usr/local/Ascend/8.5.0/compiler/bishengir/bin:$PATH
export ASCEND_HOME_PATH=/usr/local/Ascend/ascend-toolkit/latest
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export STREAMS_PER_DEVICE=32
MODEL_PATH=xxx
export SGLANG_NPU_USE_MULTI_STREAM=1
export SGLANG_NPU_USE_MLAPO=1
export HCCL_OP_EXPANSION_MODE=AIV
export SGLANG_SCHEDULER_SKIP_ALL_GATHER=1
export TASK_QUEUE_ENABLE=0
export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
export SGLANG_ENABLE_SPEC_V2=1
IPs=('your decode ip1' 'your decode ip2')
export prefill_ip=your prefill ip1
# get IP in current node
LOCAL_HOST=`hostname -I|awk -F " " '{print$1}'`
echo "LOCAL_HOST = " ${LOCAL_HOST}
# get node index
for i in "${!IPs[@]}";
# decode
for i in "${!D_IP[@]}";
do
echo "LOCAL_HOST=${LOCAL_HOST}, IPs[${i}]=${IPs[$i]}"
if [ "$LOCAL_HOST" == "${IPs[$i]}" ]; then
echo "Node Rank : ${i}"
VC_TASK_INDEX=$i
break
fi
if [[ "$LOCAL_HOST1" == "${D_IP[$i]}" || "$LOCAL_HOST2" == "${D_IP[$i]}" ]];
then
echo "${D_IP[$i]}"
export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
export SGLANG_ENABLE_SPEC_V2=1
export TASK_QUEUE_ENABLE=0
export SGLANG_SCHEDULER_SKIP_ALL_GATHER=1
export HCCL_SOCKET_IFNAME=xxx
export GLOO_SOCKET_IFNAME=xxx
DP=8
export HCCL_BUFFSIZE=400
export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=8
python3 -m sglang.launch_server --model-path ${MODEL_PATH} \
--tp 32 \
--dp ${DP} \
--ep 32 \
--moe-dense-tp-size 1 \
--enable-dp-attention \
--enable-dp-lm-head \
--trust-remote-code \
--attention-backend ascend \
--device npu \
--watchdog-timeout 9000 \
--host ${D_IP[$i]} --port 8001 \
--mem-fraction-static 0.79 \
--disable-radix-cache \
--chunked-prefill-size -1 --max-prefill-tokens 68000 \
--max-running-requests 32 \
--cuda-graph-max-bs 4 \
--moe-a2a-backend deepep \
--deepep-mode low_latency \
--quantization modelslim \
--speculative-algorithm NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 \
--disaggregation-transfer-backend ascend \
--disaggregation-mode decode \
--nnodes 2 --node-rank $i \
--prefill-round-robin-balance \
--dist-init-addr ${D_IP[0]}:10000
break
fi
done
IFNAMES=('xxx' 'xxx')
export HCCL_SOCKET_IFNAME=${IFNAMES[$VC_TASK_INDEX]}
export GLOO_SOCKET_IFNAME=${HCCL_SOCKET_IFNAME}
nnodes=${#IPs[@]}
tp_size=`expr 16 \* ${nnodes}`
export ASCEND_MF_STORE_URL=tcp://${prefill_ip}:24667
CHUNKED_SIZE=65536
DP=8
export HCCL_BUFFSIZE=400
export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=8
python3 -m sglang.launch_server --model-path ${MODEL_PATH} \
--tp $tp_size \
--dp ${DP} \
--ep $tp_size \
--moe-dense-tp-size 1 \
--enable-dp-attention \
--enable-dp-lm-head \
--trust-remote-code \
--attention-backend ascend \
--device npu \
--watchdog-timeout 9000 \
--host ${IPs[$VC_TASK_INDEX]} --port 8001 \
--mem-fraction-static 0.79 \
--disable-radix-cache \
--chunked-prefill-size -1 --max-prefill-tokens 68000 \
--max-running-requests 32 \
--cuda-graph-max-bs 4 \
--moe-a2a-backend deepep \
--deepep-mode low_latency \
--quantization modelslim \
--speculative-algorithm NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 \
--disaggregation-transfer-backend ascend \
--disaggregation-mode decode \
--load-balance-method round_robin \
--nnodes $nnodes --node-rank $VC_TASK_INDEX \
--dist-init-addr ${IPs[0]}:10000 --load-balance-method decode_round_robin
```
```shell
export SGLANG_DP_ROUND_ROBIN=1
python -m sglang_router.launch_router \
--pd-disaggregation \
--policy cache_aware \
--prefill http://PIP1:8000 8995 \
--decode http://DIP1:8001 \
--prefill http://P_IP1:8000 8995 \
--decode http://D_IP1:8001 \
--host 127.0.0.1 \
--port 6688 \
--mini-lb
@@ -986,7 +934,7 @@ python -m sglang_router.launch_router \
We tested it based on the `RANDOM` dataset.
```shell
python -m sglang.bench_serving --dataset-name random --backend sglang --host 127.0.0.1 --port 6688 --max-concurrency 32 --random-input-len 64000 --random-output-len 3000 --num-prompts 64 --random-range-ratio 1
python -m sglang.bench_serving --dataset-name random --backend sglang --host 127.0.0.1 --port 6688 --max-concurrency 8 --random-input-len 131076 --random-output-len 1024 --num-prompts 8 --random-range-ratio 1
```
### Qwen3-235B-A22B 3_5K-1_5K 50ms on A3 24 Cards Separation Mode