| 硬件 | 类型 |
|---|---|
| hardware | NPU |
GLM-5.3-Flash-w8a8 是智谱 AI(Z.ai)GLM-5 系列首个原生多模态模型 GLM-5.3-Flash 的 W8A8 量化部署版本。
部署方式:
| 项目 | 规格 |
|---|---|
| NPU 型号 | Ascend 910B3 |
| NPU 数量 | 32(单机 8 卡) |
| 单卡 HBM | 64 GB |
| 单机 HBM 总量(8 卡) | 512 GB |
| 架构 | aarch64 |
| 操作系统 | Ubuntu 22.04.5 LTS (aarch64) |
| 组件 | 版本 |
|---|---|
| npu-smi | 25.5.1 |
| CANN Toolkit | 9.2.0 |
| torch | 2.10.0+cpu |
| torch_npu | 2.10.0.post7 |
| vLLM | 0.30.0 |
| vllm-ascend | 0.30.0rc2 |
| Python | 3.12.13 aarch64 Linux |
| 项目 | 取值 |
|---|---|
| 模型名称 | GLM-5.3-w8a8 |
| 模型获取链接 | https://modelscope.cn/models/Eco-Tech/GLM-5.3-Flash-w8a8 |
模型权重下载脚本参考:
nohup modelscope download --model Eco-Tech/GLM-5.3-Flash-w8a8 --local_dir /mnt/sfs_turbo/GLM-5.3-w8a8/GLM-5.3-Flash-w8a8-1013 > down_glm53-flash-w8a8.log 2>&1 &容器部署脚本参考:
export IMAGE=quay.io/ascend/vllm-ascend:v0.30.0rc2
export NAME=glm53-flash-030rc2
docker run \
--name $NAME \
--net=host \
--shm-size=500g \
--privileged \
--device /dev/davinci0 \
--device /dev/davinci1 \
--device /dev/davinci2 \
--device /dev/davinci3 \
--device /dev/davinci4 \
--device /dev/davinci5 \
--device /dev/davinci6 \
--device /dev/davinci7 \
--device /dev/davinci_manager \
--device /dev/devmm_svm \
--device /dev/hisi_hdc \
-v /usr/local/Ascend/driver:/usr/local/Ascend/driver \
-v /usr/local/Ascend/firmware:/usr/local/Ascend/firmware \
-v /usr/local/sbin/npu-smi:/usr/local/sbin/npu-smi \
-v /usr/local/sbin:/usr/local/sbin \
-v /etc/hccn.conf:/etc/hccn.conf:ro \
-itd $IMAGE bashMoonCake master进程启动脚本参考(在P主节点启动):
#!/usr/bin/env bash
mooncake_master \
--port 50088 \
--eviction_high_watermark_ratio 0.95 \
--eviction_ratio 0.1 \
--default_kv_lease_ttl 120s \
--enable_offload=false \
--client_ttl=600 \
--alsologtostderr > start_mooncake-master.fix.log 2>&1 &
各节点的mooncake.json配置文件配置参考:
{
"metadata_server": "P2PHANDSHAKE",
"protocol": "ascend",
"device_name": "",
"master_server_address": "${Mooncake master的IP}:50088",
"global_segment_size": "64GB",
"local_buffer_size": "16GB",
"preferred_segment": true,
"prefer_alloc_in_same_node": true,
"enable_ssd_offload": false,
"tenant_id": "default"
}部署方案:使用prefill:dp_size: 2,tp_size: 8,dp-size-local 1,decode: dp_size: 8,tp_size: 2,dp-size-local 4,为1P4D部署方案。
import argparse
import multiprocessing
import subprocess
def parse_args():
parser = argparse.ArgumentParser()
parser.add_argument("--template", default="./run_p.sh")
parser.add_argument("--dp-size", type=int, required=True)
parser.add_argument("--tp-size", type=int, default=1)
parser.add_argument("--dp-size-local", type=int, default=-1)
parser.add_argument("--dp-rank-start", type=int, default=0)
parser.add_argument("--dp-address", required=True)
parser.add_argument("--dp-rpc-port", default="12325")
parser.add_argument("--vllm-start-port", type=int, default=8000)
args = parser.parse_args()
if args.dp_size_local == -1:
args.dp_size_local = args.dp_size
return args
def run(args, devices, port, dp_rank):
subprocess.run(
[
"bash",
args.template,
devices,
str(port),
str(args.dp_size),
str(dp_rank),
args.dp_address,
args.dp_rpc_port,
str(args.tp_size),
],
check=True,
)
if __name__ == "__main__":
args = parse_args()
processes = []
for i in range(args.dp_size_local):
devices = ",".join(
str(device)
for device in range(i * args.tp_size, (i + 1) * args.tp_size)
)
process = multiprocessing.Process(
target=run,
args=(
args,
devices,
args.vllm_start_port + i,
args.dp_rank_start + i,
),
)
processes.append(process)
process.start()
for process in processes:
process.join()A2 系列节点不具备 A3 的 HCCS 网络,缓存池通过 A2 RoCE 网络运行,在配置中增加 export HCCL_INTRA_ROCE_ENABLE=1配置:
#!/usr/bin/env bash
# Usage: bash run_p.sh <visible_devices> <http_port> <dp_size> \
# <dp_rank> <dp_address> <rpc_port> <tp_size>
: "${LOCAL_IP:?Set LOCAL_IP in the P0 or P1 wrapper}"
: "${NIC_NAME:?Set NIC_NAME in the P0 or P1 wrapper}"
: "${MODEL_PATH:?Set MODEL_PATH in the P0 or P1 wrapper}"
export HCCL_IF_IP="$LOCAL_IP"
export GLOO_SOCKET_IFNAME="$NIC_NAME"
export TP_SOCKET_IFNAME="$NIC_NAME"
export HCCL_SOCKET_IFNAME="$NIC_NAME"
export VLLM_HOST_IP="$LOCAL_IP"
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export VLLM_SERVER_DEV_MODE=1
export VLLM_USE_V2_MODEL_RUNNER=0
export HCCL_OP_EXPANSION_MODE=AIV
export HCCL_BUFFSIZE=1024
export VLLM_EXECUTE_MODEL_TIMEOUT_SECONDS=3000
export HCCL_EXEC_TIMEOUT=3600
export HCCL_CONNECT_TIMEOUT=1200
export VLLM_RPC_TIMEOUT=3600000
export OMP_PROC_BIND=false
export OMP_NUM_THREADS=10
export ASCEND_RT_VISIBLE_DEVICES="$1"
export TASK_QUEUE_ENABLE=2
export HCCL_INTRA_ROCE_ENABLE=1
export ASCEND_TRANSFER_TIMEOUT=120000
export VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT="${VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT:-300}"
export PYTHONHASHSEED=0
export MOONCAKE_CONFIG_PATH="${本地mooncake.json路径}/mooncake.json"
exec vllm serve "$MODEL_PATH" \
--host 0.0.0.0 \
--port "$2" \
--data-parallel-size "$3" \
--data-parallel-size-local 1 \
--data-parallel-address "$5" \
--data-parallel-rpc-port "$6" \
--tensor-parallel-size "$7" \
--enable-expert-parallel \
--enable-chunked-prefill \
--enable-prefix-caching \
--seed 1024 \
--served-model-name glm53-flash \
--safetensors-load-strategy prefetch \
--max-model-len 1000000 \
--max-num-seqs 64 \
--max-num-batched-tokens 8192 \
--trust-remote-code \
--quantization ascend \
--kv-cache-dtype int8 \
--attention_config.indexer_kv_dtype int8 \
--limit-mm-per-prompt '{"image":1,"video":0}' \
--gpu-memory-utilization 0.9 \
--async-scheduling \
--enforce-eager \
--tool-call-parser glm47 \
--reasoning-parser glm47 \
--enable-auto-tool-choice \
--speculative-config '{"num_speculative_tokens": 5, "method": "deepseek_mtp", "enforce_eager": true}' \
${SERVER_ROLE_ARGS:-} \
--compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}' \
--additional-config '{"enable_flashcomm1": true,"mc2_comm_alg": "hierarchy","enable_dsa_cp": true,"enable_fused_mc2": 0, "ascend_compilation_config": {"enable_npugraph_ex": true, "enable_static_kernel": false}, "multistream_overlap_shared_expert": true, "enable_mc2_hierarchy_comm": false,"enable_sparse_sfa_c8": true, "enable_sparse_li_c8": true, "enable_cpu_binding": true, "recompute_scheduler_enable": false}' \
--kv-transfer-config \
'{
"kv_connector": "MultiConnector",
"kv_role": "kv_producer",
"engine_id": "0",
"kv_connector_extra_config": {
"connectors": [
{
"kv_connector": "MooncakeConnectorV2",
"kv_role": "kv_producer",
"kv_port": "30000",
"kv_connector_extra_config": {
"use_ascend_direct": true,
"prefill": {"dp_size": 2, "tp_size": 8},
"decode": {"dp_size": 8, "tp_size": 2}
}
},
{
"kv_connector": "AscendStoreConnector",
"kv_role": "kv_producer",
"kv_connector_extra_config": {
"backend": "mooncake",
"use_layerwise": false,
"lookup_rpc_port": '"$((37000 + $4))"'
}
}
]
}
}'
--prefix-cache-retention-interval NoneA2 系列节点不具备 A3 的 HCCS 网络,缓存池通过 A2 RoCE 网络运行,在配置中增加 export HCCL_INTRA_ROCE_ENABLE=1配置:
#!/usr/bin/env bash
# Usage: bash run_d.sh <visible_devices> <http_port> <dp_size> \
# <dp_rank> <dp_address> <rpc_port> <tp_size>
: "${LOCAL_IP:?Set LOCAL_IP in the D0 or D1 wrapper}"
: "${NIC_NAME:?Set NIC_NAME in the D0 or D1 wrapper}"
: "${MODEL_PATH:?Set MODEL_PATH in the D0 or D1 wrapper}"
export HCCL_IF_IP="$LOCAL_IP"
export GLOO_SOCKET_IFNAME="$NIC_NAME"
export TP_SOCKET_IFNAME="$NIC_NAME"
export HCCL_SOCKET_IFNAME="$NIC_NAME"
export VLLM_HOST_IP="$LOCAL_IP"
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True,pin_memory_expandable_segments:True
export VLLM_SERVER_DEV_MODE=1
export VLLM_USE_V2_MODEL_RUNNER=0
export HCCL_OP_EXPANSION_MODE=AIV
export HCCL_BUFFSIZE=1024
export VLLM_EXECUTE_MODEL_TIMEOUT_SECONDS=3000
export HCCL_EXEC_TIMEOUT=3600
export HCCL_CONNECT_TIMEOUT=1200
export VLLM_RPC_TIMEOUT=3600000
export OMP_PROC_BIND=false
export OMP_NUM_THREADS=10
# Reserve disjoint HCCL port ranges per DP rank so multiple engines on
# one node never share host/NPU socket ports.
export HCCL_HOST_SOCKET_PORT_RANGE="$((60000 + $4 * 100))-$((60099 + $4 * 100))"
export HCCL_NPU_SOCKET_PORT_RANGE="$((60000 + $4 * 100))-$((60099 + $4 * 100))"
export ASCEND_RT_VISIBLE_DEVICES="$1"
export HCCL_INTRA_ROCE_ENABLE=1
export ASCEND_TRANSFER_TIMEOUT=120000
export VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT="${VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT:-300}"
export PYTHONHASHSEED=0
export MOONCAKE_CONFIG_PATH="${本地mooncake.json路径}/mooncake.json"
exec vllm serve "$MODEL_PATH" \
--host 0.0.0.0 \
--port "$2" \
--data-parallel-size "$3" \
--data-parallel-rank "$4" \
--data-parallel-address "$5" \
--data-parallel-rpc-port "$6" \
--tensor-parallel-size "$7" \
--enable-expert-parallel \
--enable-chunked-prefill \
--enable-prefix-caching \
--seed 1024 \
--served-model-name glm53-flash \
--safetensors-load-strategy prefetch \
--max-model-len 1000000 \
--max-num-seqs 32 \
--max-num-batched-tokens 1024 \
--trust-remote-code \
--quantization ascend \
--kv-cache-dtype int8 \
--attention_config.indexer_kv_dtype int8 \
--gpu-memory-utilization 0.85 \
--skip-mm-profiling \
--limit-mm-per-prompt '{"image":1,"video":0}' \
--async-scheduling \
--tool-call-parser glm47 \
--reasoning-parser glm47 \
--enable-auto-tool-choice \
--compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}' \
--additional-config '{"enable_flashcomm1": false, "mc2_comm_alg": "hierarchy","enable_dsa_cp": false, "ascend_compilation_config": {"enable_npugraph_ex": true, "enable_static_kernel": false}, "multistream_overlap_shared_expert": true, "enable_mc2_hierarchy_comm": false, "enable_sparse_sfa_c8": true, "enable_sparse_li_c8": true, "enable_cpu_binding": true, "recompute_scheduler_enable": true}' \
--speculative-config '{"num_speculative_tokens": 5, "method": "deepseek_mtp", "enforce_eager": true}' \
--kv-transfer-config \
'{
"kv_connector": "MultiConnector",
"kv_role": "kv_consumer",
"engine_id": "1",
"kv_connector_extra_config": {
"connectors": [
{
"kv_connector": "MooncakeConnectorV2",
"kv_role": "kv_consumer",
"kv_port": "30100",
"kv_connector_extra_config": {
"use_ascend_direct": true,
"prefill": {"dp_size": 2, "tp_size": 8},
"decode": {"dp_size": 8, "tp_size": 2}
}
},
{
"kv_connector": "AscendStoreConnector",
"kv_role": "kv_consumer",
"kv_connector_extra_config": {
"backend": "mooncake",
"use_layerwise": false,
"consumer_is_to_load": false,
"consumer_is_to_put": false,
"lookup_rpc_port": '"$((37100 + $4))"'
}
}
]
}
}'
--prefix-cache-retention-interval Noneprefill0节点需要配置"--api-server-count 1",IP,eth分别为prefill0节点的IP和网卡名,还需要正确配置权重路径:
#!/usr/bin/env bash
export LOCAL_IP="${IP}"
export NIC_NAME="${eth}"
export MODEL_PATH="${权重目录}/GLM-5.3-Flash-w8a8-1013"
export SERVER_ROLE_ARGS="--api-server-count 1"
exec bash ./run_p.sh "$@"prefill1节点需要配置"--headless --data-parallel-start-rank 1",IP,eth分别为prefill1节点的IP和网卡名,还需要正确配置权重路径:
#!/usr/bin/env bash
export LOCAL_IP="${IP}"
export NIC_NAME="${eth}"
export MODEL_PATH="${权重目录}/GLM-5.3-Flash-w8a8-1013"
export SERVER_ROLE_ARGS="--headless --data-parallel-start-rank 1"
exec bash ./run_p.sh "$@"IP,eth分别为prefill0节点的IP
cd "$(dirname "$0")"
LOG_DIR=/mnt/modeltest-glm53-flash-pd-mem
mkdir -p $LOG_DIR
LAUNCHER_LOG=$LOG_DIR/node0_p_launcher.log
nohup python launch_online_dp.py \
--template ./run_p0.sh \
--dp-size 2 \
--tp-size 8 \
--dp-size-local 1 \
--dp-rank-start 0 \
--dp-address ${IP} \
--dp-rpc-port 12321 \
--vllm-start-port 9081 > $LAUNCHER_LOG 2>&1 &IP,eth分别为prefill0节点的IP
cd "$(dirname "$0")"
LOG_DIR=/mnt/modeltest-glm53-flash-pd-mem
mkdir -p $LOG_DIR
LAUNCHER_LOG=$LOG_DIR/node1_p_launcher.log
nohup python launch_online_dp.py \
--template ./run_p1.sh \
--dp-size 2 \
--tp-size 8 \
--dp-size-local 1 \
--dp-rank-start 1 \
--dp-address ${IP} \
--dp-rpc-port 12321 \
--vllm-start-port 9082 > $LAUNCHER_LOG 2>&1 &IP,eth分别为decode0节点的IP
#!/usr/bin/env bash
export LOCAL_IP="${IP}"
export NIC_NAME="${eth}"
export MODEL_PATH="${模型权重地址}/GLM-5.3-Flash-w8a8-1013"
exec bash ./run_d.sh "$@"IP,eth分别为decode1节点的IP
#!/usr/bin/env bash
export LOCAL_IP="${IP}"
export NIC_NAME="${eth}"
export MODEL_PATH="${模型权重地址}/GLM-5.3-Flash-w8a8-1013"
exec bash ./run_d.sh "$@"其中decode0_IP需要配置为decode0节点的IP:
cd "$(dirname "$0")"
LOG_DIR=/mnt/modeltest-glm53-flash-pd-mem
mkdir -p $LOG_DIR
LAUNCHER_LOG=$LOG_DIR/node2_d_launcher.log
nohup python launch_online_dp.py \
--template ./run_d0.sh \
--dp-size 8 \
--tp-size 2 \
--dp-size-local 4 \
--dp-rank-start 0 \
--dp-address ${decode0_IP} \
--dp-rpc-port 12321 \
--vllm-start-port 9900 > $LAUNCHER_LOG 2>&1 &其中decode0_IP需要配置为decode0节点的IP:
cd "$(dirname "$0")"
LOG_DIR=/mnt/modeltest-glm53-flash-pd-mem
mkdir -p $LOG_DIR
LAUNCHER_LOG=$LOG_DIR/node3_d_launcher.log
nohup python launch_online_dp.py \
--template ./run_d1.sh \
--dp-size 8 \
--tp-size 2 \
--dp-size-local 4 \
--dp-rank-start 4 \
--dp-address ${decode0_IP} \
--dp-rpc-port 12321 \
--vllm-start-port 9900 > $LAUNCHER_LOG 2>&1 &cd "$(dirname "$0")"
unset ftp_proxy
unset https_proxy
unset http_proxy
LOG_DIR=/mnt/modeltest-glm53-flash-pd-mem
mkdir -p $LOG_DIR
PROXY_LOG=$LOG_DIR/proxy_18000.log
nohup python /vllm-workspace/vllm-ascend/examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py \
--port 18000 \
--host 0.0.0.0 \
--prefiller-hosts \
${prefill0_IP} \
--prefiller-ports \
9081 \
--decoder-hosts \
${decode0_IP} \
${decode0_IP} \
${decode0_IP} \
${decode0_IP} \
${decode1_IP} \
${decode1_IP} \
${decode1_IP} \
${decode1_IP} \
--decoder-ports \
9900 9901 9902 9903 \
9900 9901 9902 9903 > $PROXY_LOG 2>&1 &推理请求及报文:
curl http://{prefill0_IP}:18000/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "glm53-flash",
"messages": [{"role": "user", "content": "Who are you?"}],
"max_tokens": 256,
"temperature": 0
}'