From 71b090a8e785c3ff74cafa6a9345e6d6f9c57b09 Mon Sep 17 00:00:00 2001
From: chenxu214 <justin_cc2025@163.com>
Date: Wed, 17 Jun 2026 09:55:50 +0800
Subject: [PATCH] [Ascend]GLM 5.2 deployment (#28433)

---
 .../ascend_npu_glm5.2_examples.mdx            | 376 ++++++++++++++++++
 1 file changed, 376 insertions(+)
 create mode 100644 docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_glm5.2_examples.mdx

diff --git a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_glm5.2_examples.mdx b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_glm5.2_examples.mdx
new file mode 100644
index 000000000..cb83c36bf
--- /dev/null
+++ b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_glm5.2_examples.mdx
@@ -0,0 +1,376 @@
+# GLM-5.2 examples
+
+## Introduction
+
+The GLM (General Language Model) series is an open-source bilingual large language model family jointly developed by the KEG Laboratory of Tsinghua University and Zhipu AI. This series of models has performed outstandingly in the field of Chinese NLP with its unique unified pre-training framework and bilingual capabilities. GLM-5.2 adopts the DeepSeek-V3/V3.2 architecture, including the sparse attention (DSA) and multi-token prediction (MTP). Ascend supports GLM-5.2 with 0Day based on the SGLang inference framework, achieving low-code seamless enablement and compatibility with the mainstream distributed parallel capabilities within the current SGLang framework. We welcome developers to download and experience it.
+
+## Environment Preparation
+
+### Model Weight
+
+- `GLM-5.2`(BF16 version): [Download model weight](https://huggingface.co/collections/zai-org/glm-52).
+- `GLM-5.2-w8a8`(Quantized version without mtp): [Download model weight](https://www.modelscope.cn/models/Eco-Tech/GLM-5.2-w8a8/).
+- You can use [msmodelslim](https://gitcode.com/Ascend/msmodelslim) to quantify the model naively.
+
+
+### Installation
+
+The dependencies required for the NPU runtime environment have been integrated into a Docker image and uploaded to the online platform. You can directly pull it.
+
+```{code-block} bash
+#Atlas 800 A3
+docker pull swr.cn-southwest-2.myhuaweicloud.com/base_image/dockerhub/lmsysorg/sglang:cann9.0.0-a3-glm5.2-20260615
+#Atlas 800 A2
+docker pull swr.cn-southwest-2.myhuaweicloud.com/base_image/dockerhub/lmsysorg/sglang:cann9.0.0-910b-glm5.2-20260615
+
+#start container
+docker run -itd --shm-size=16g --privileged=true --name ${NAME} \
+--privileged=true --net=host \
+-v /var/queue_schedule:/var/queue_schedule \
+-v /etc/ascend_install.info:/etc/ascend_install.info \
+-v /usr/local/sbin:/usr/local/sbin \
+-v /usr/local/Ascend/driver:/usr/local/Ascend/driver \
+-v /usr/local/Ascend/firmware:/usr/local/Ascend/firmware \
+--device=/dev/davinci0:/dev/davinci0  \
+--device=/dev/davinci1:/dev/davinci1  \
+--device=/dev/davinci2:/dev/davinci2  \
+--device=/dev/davinci3:/dev/davinci3  \
+--device=/dev/davinci4:/dev/davinci4  \
+--device=/dev/davinci5:/dev/davinci5  \
+--device=/dev/davinci6:/dev/davinci6  \
+--device=/dev/davinci7:/dev/davinci7  \
+--device=/dev/davinci8:/dev/davinci8  \
+--device=/dev/davinci9:/dev/davinci9  \
+--device=/dev/davinci10:/dev/davinci10  \
+--device=/dev/davinci11:/dev/davinci11  \
+--device=/dev/davinci12:/dev/davinci12  \
+--device=/dev/davinci13:/dev/davinci13  \
+--device=/dev/davinci14:/dev/davinci14  \
+--device=/dev/davinci15:/dev/davinci15  \
+--device=/dev/davinci_manager:/dev/davinci_manager \
+--device=/dev/hisi_hdc:/dev/hisi_hdc \
+--entrypoint=bash \
+swr.cn-southwest-2.myhuaweicloud.com/base_image/dockerhub/lmsysorg/sglang:${TAG}
+```
+
+## Deployment
+
+### Single-node Deployment
+
+- Quantized model `glm5.2_w8a8` can be deployed on 1 Atlas 800 A3 (64G × 16) .
+
+**A3 series**
+
+Run the following script to execute online inference.
+
+```shell
+# high performance cpu
+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
+# bind cpu
+export SGLANG_SET_CPU_AFFINITY=1
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+# cann
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export STREAMS_PER_DEVICE=32
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+export SGLANG_ENABLE_SPEC_V2=1
+# MTP OVERLAP
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+export SGLANG_NPU_USE_MULTI_STREAM=1
+
+export HCCL_BUFFSIZE=1000
+export HCCL_OP_EXPANSION_MODE=AIV
+export HCCL_SOCKET_IFNAME=lo
+export GLOO_SOCKET_IFNAME=lo
+# DEEPEP
+export DEEPEP_NORMAL_LONG_SEQ_ROUND=72
+export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=1024
+export DEEPEP_NORMAL_COMBINE_ENABLE_LONG_SEQ=1
+
+MODEL_PATH={"weights path"}
+
+python3 -m sglang.launch_server \
+        --model-path $MODEL_PATH \
+        --attention-backend ascend \
+        --device npu \
+        --tp-size 16 --nnodes 1 --node-rank 0 \
+        --chunked-prefill-size 16384 --max-prefill-tokens 280000 \
+        --trust-remote-code \
+        --host 127.0.0.1 \
+        --mem-fraction-static 0.7 \
+        --port 8000 \
+        --served-model-name glm-5 \
+        --cuda-graph-bs 16 \
+        --quantization modelslim \
+        --speculative-draft-model-quantization unquant \
+        --speculative-algorithm NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4  \
+        --moe-a2a-backend deepep --deepep-mode auto
+```
+
+**A2 series**
+
+Run the following script to execute online inference.
+```shell
+export SGLANG_SET_CPU_AFFINITY=1
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+# cann
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export STREAMS_PER_DEVICE=32
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+
+export HCCL_BUFFSIZE=1000
+export HCCL_SOCKET_IFNAME=lo
+export GLOO_SOCKET_IFNAME=lo
+export TRANSFORMERS_VERBOSITY=error
+
+#DEEPEP
+export DEEPEP_NORMAL_LONG_SEQ_ROUND=72
+export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=1024
+export DEEPEP_NORMAL_COMBINE_ENABLE_LONG_SEQ=1
+export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+
+MODEL_PATH={"weights path"}
+
+python3 -m sglang.launch_server \
+        --model-path $MODEL_PATH \
+        --attention-backend ascend \
+        --device npu \
+        --tp-size 8 \
+        --nnodes 1 \
+        --dp-size 1 \
+        --enable-dp-attention \
+        --chunked-prefill-size -1 \
+        --max-prefill-tokens 65536 \
+        --trust-remote-code \
+        --mem-fraction-static 0.9 \
+        --served-model-name glm-5 \
+        --cuda-graph-bs 8 \
+        --max-running-requests 102 \
+        --quantization modelslim \
+        --speculative-draft-model-quantization unquant \
+        --moe-a2a-backend deepep --deepep-mode auto \
+        --load-balance-method round_robin
+```
+
+### Multi-node Deployment
+
+- Quantized model `glm5.2_w8a8` can be deployed on 2 Atlas 800 A3 (64G × 16) .
+
+**A3 series**
+
+Modify the IP of 2 nodes, then run the same scripts on two nodes.
+
+**node 0/1**
+
+```shell
+echo performance | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
+sysctl -w vm.swappiness=0
+sysctl -w kernel.numa_balancing=0
+sysctl -w kernel.sched_migration_cost_ns=50000
+# bind cpu
+export SGLANG_SET_CPU_AFFINITY=1
+
+unset https_proxy
+unset http_proxy
+unset HTTPS_PROXY
+unset HTTP_PROXY
+unset ASCEND_LAUNCH_BLOCKING
+# cann
+source /usr/local/Ascend/ascend-toolkit/set_env.sh
+source /usr/local/Ascend/nnal/atb/set_env.sh
+
+export STREAMS_PER_DEVICE=32
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+# MTP OVERLAP
+export SGLANG_ENABLE_SPEC_V2=1
+export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
+
+export SGLANG_NPU_USE_MULTI_STREAM=1
+export HCCL_BUFFSIZE=1000
+export HCCL_OP_EXPANSION_MODE=AIV
+
+# Run command ifconfig on two nodes, find out which inet addr has same IP with your node IP. That is your public interface, which should be added here
+export HCCL_SOCKET_IFNAME=lo
+export GLOO_SOCKET_IFNAME=lo
+
+# DEEPEP
+export DEEPEP_NORMAL_LONG_SEQ_ROUND=72
+export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=1024
+export DEEPEP_NORMAL_COMBINE_ENABLE_LONG_SEQ=1
+
+
+IPS=('your ip1' 'your ip2')
+IP_MASTER="${IPS[0]}:your port"
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+
+MODEL_PATH={"weights path"}
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+for i in "${!IPS[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${IPS[$i]}" || "$LOCAL_HOST2" == "${IPS[$i]}" ]];
+    then
+        echo "${IPS[$i]}"
+        python3 -m sglang.launch_server \
+        --model-path $MODEL_PATH \
+        --attention-backend ascend \
+        --device npu \
+        --tp-size 32 --nnodes 2 --node-rank $i --dist-init-addr $IP_MASTER \
+        --chunked-prefill-size 16384 --max-prefill-tokens 131072 \
+        --trust-remote-code \
+        --host 127.0.0.1 \
+        --mem-fraction-static 0.8 \
+        --port 8000 \
+        --served-model-name glm-5 \
+        --cuda-graph-max-bs 32 \
+        --moe-a2a-backend deepep \
+        --deepep-mode auto \
+        --speculative-draft-model-quantization unquant \
+        --speculative-algorithm NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4  \
+        --disable-radix-cache
+        NODE_RANK=$i
+        break
+    fi
+done
+
+```
+
+### Prefill-Decode Disaggregation
+
+```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 PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export STREAMS_PER_DEVICE=32
+# pd transfer, prefill master IP
+export ASCEND_MF_STORE_URL="tcp://x.x.x.x:24707"
+export SGLANG_DISAGGREGATION_BOOTSTRAP_TIMEOUT=600
+
+P_IP=('your ip1')
+D_IP=('your ip2')
+
+MODEL_PATH={"weights path"}
+
+export TRANSFORMERS_VERBOSITY=error
+
+LOCAL_HOST1=`hostname -I|awk -F " " '{print$1}'`
+LOCAL_HOST2=`hostname -I|awk -F " " '{print$2}'`
+echo "${LOCAL_HOST1}"
+echo "${LOCAL_HOST2}"
+
+# prefill
+for i in "${!P_IP[@]}";
+do
+    if [[ "$LOCAL_HOST1" == "${P_IP[$i]}" || "$LOCAL_HOST2" == "${P_IP[$i]}" ]];
+    then
+        echo "${P_IP[$i]}"
+        export DEEPEP_NORMAL_LONG_SEQ_ROUND=72
+        export DEEPEP_NORMAL_LONG_SEQ_PER_ROUND_TOKENS=1024
+        export DEEPEP_NORMAL_COMBINE_ENABLE_LONG_SEQ=1
+        export DEEP_NORMAL_MODE_USE_INT8_QUANT=1
+        export TASK_QUEUE_ENABLE=2
+        export HCCL_SOCKET_IFNAME=lo
+        export GLOO_SOCKET_IFNAME=lo
+
+        # P节点
+        python -m sglang.launch_server --model-path ${MODEL_PATH}  --disaggregation-mode prefill --host ${P_IP[$i]} \
+        --port 8000 --disaggregation-bootstrap-port 8998 --trust-remote-code --nnodes 1 --node-rank $i \
+        --tp-size 16 --mem-fraction-static 0.8 --attention-backend ascend --device npu --quantization modelslim \
+        --disaggregation-transfer-backend ascend --max-running-requests 64 \
+        --served-model-name glm-5 --chunked-prefill-size 524288 --max-prefill-tokens 180000 --moe-a2a-backend deepep --deepep-mode normal \
+        --disable-shared-experts-fusion --disable-cuda-graph --dtype bfloat16 \
+        --dp-size 4 --enable-dp-attention \
+        --load-balance-method round_robin \
+        --enable-dp-lm-head --moe-dense-tp 1 \
+        --speculative-draft-model-quantization unquant \
+        --speculative-algorithm NEXTN --speculative-num-steps 1 --speculative-eagle-topk 1 --speculative-num-draft-tokens 2 \
+
+        # cp
+        #--enable-nsa-prefill-context-parallel \
+        #--nsa-prefill-cp-mode in-seq-split \
+        #--attn-cp-size 4 \
+        NODE_RANK=$i
+        break
+    fi
+done
+
+# decode
+for i in "${!D_IP[@]}";
+do
+    if [[ "$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 HCCL_BUFFSIZE=650
+
+        export SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=32
+        export TASK_QUEUE_ENABLE=0
+
+        export HCCL_SOCKET_IFNAME=lo
+        export GLOO_SOCKET_IFNAME=lo
+
+        export SGLANG_NPU_USE_MULTI_STREAM=1
+
+        python -m sglang.launch_server --model-path ${MODEL_PATH} --disaggregation-mode decode --host ${D_IP[$i]} \
+        --port 8003 --trust-remote-code --nnodes 1 --node-rank $i --tp-size 16 --dp-size 16 --ep-size 16 \
+        --mem-fraction-static 0.8 --max-running-requests 128 --attention-backend ascend --device npu --quantization modelslim \
+        --served-model-name glm-5 --moe-a2a-backend deepep --enable-dp-attention --deepep-mode low_latency \
+        --cuda-graph-max-bs 4 --disaggregation-transfer-backend ascend --watchdog-timeout 9000 --context-length 180000 \
+        --tokenizer-worker-num 4 --prefill-round-robin-balance --disable-shared-experts-fusion --dtype bfloat16  --load-balance-method round_robin \
+        --speculative-draft-model-quantization unquant \
+        --speculative-algorithm NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4
+        NODE_RANK=$i
+        break
+    fi
+done
+
+exit 1
+
+```
+
+```shell
+python3 -m sglang_router.launch_router \
+--pd-disaggregation \
+--policy round_robin \
+--prefill http://{P_MASTER_IP}:8000 8998 \
+--decode http://{D_MASTER_IP}:8003 \
+--host {P_MASTER_IP} \
+--port 6688
+```
+
+### Using Benchmark
+
+Refer to [Benchmark and Profiling](../../developer_guide/benchmark_and_profiling.md) for details.