xc-llm-ascend/docs/source/tutorials/models/GLM4.x.md

GLM-4.5/4.6/4.7

Introduction

GLM-4.x series models use a Mixture-of-Experts (MoE) architecture and are foundational models specifically designed for agent applications.

The GLM-4.5 model is first supported in vllm-ascend:v0.10.0rc1.

This document will show the main verification steps of the model, including supported features, feature configuration, environment preparation, single-node and multi-node deployment, accuracy and performance evaluation.

Supported Features

Refer to supported features to get the model's supported feature matrix.

Refer to feature guide to get the feature's configuration.

Environment Preparation

Model Weight

• GLM-4.5(BF16 version): Download model weight.
• GLM-4.6(BF16 version): Download model weight.
• GLM-4.7(BF16 version): Download model weight.
• GLM-4.5-w8a8-with-float-mtp(Quantized version with mtp): Download model weight.
• GLM-4.6-w8a8(Quantized version without mtp): Download model weight. Because vllm do not support GLM4.6 mtp in October, so we do not provide mtp version. And last month, it supported, you can use the following quantization scheme to add mtp weights to Quantized weights.
• GLM-4.7-w8a8-with-float-mtp(Quantized version without mtp): Download model weight.
• Method of Quantify: quantization scheme. You can use these methods to quantify the model.

It is recommended to download the model weight to the shared directory of multiple nodes, such as /root/.cache/.

Installation

You can use our official docker image to run GLM-4.x directly.

Select an image based on your machine type and start the docker image on your node, refer to using docker.

   :substitutions:
# Update --device according to your device (Atlas A2: /dev/davinci[0-7] Atlas A3:/dev/davinci[0-15]).
# Update the vllm-ascend image according to your environment.
# Note you should download the weight to /root/.cache in advance.
# Update the vllm-ascend image
export IMAGE=m.daocloud.io/quay.io/ascend/vllm-ascend:|vllm_ascend_version|
export NAME=vllm-ascend

# Run the container using the defined variables
# Note: If you are running bridge network with docker, please expose available ports for multiple nodes communication in advance.
docker run --rm \
--name $NAME \
--net=host \
--shm-size=1g \
--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/dcmi:/usr/local/dcmi \
-v /usr/local/Ascend/driver/tools/hccn_tool:/usr/local/Ascend/driver/tools/hccn_tool \
-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
-v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
-v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
-v /etc/ascend_install.info:/etc/ascend_install.info \
-v /root/.cache:/root/.cache \
-it $IMAGE bash

Deployment

Single-node Deployment

• In low-latency scenarios, we recommend a single-machine deployment.
• Quantized model glm4.7_w8a8_with_float_mtp can be deployed on 1 Atlas 800 A3 (64G × 16) or 1 Atlas 800 A2 (64G × 8).

Run the following script to execute online inference.

#!/bin/sh
export HCCL_BUFFSIZE=512
export OMP_PROC_BIND=false
export OMP_NUM_THREADS=1
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export HCCL_OP_EXPANSION_MODE=AIV
export VLLM_ASCEND_BALANCE_SCHEDULING=1
export VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE=1
export VLLM_ASCEND_ENABLE_FLASHCOMM1=1
export VLLM_ASCEND_ENABLE_FUSED_MC2=1

vllm serve Eco-Tech/GLM-4.7-W8A8-floatmtp \
  --data-parallel-size 2 \
  --tensor-parallel-size 8 \
  --enable-expert-parallel \
  --seed 1024 \
  --served-model-name glm \
  --max-model-len 133000 \
  --max-num-batched-tokens 8192 \
  --max-num-seqs 16 \
  --async-scheduling \
  --quantization ascend \
  --trust-remote-code \
  --gpu-memory-utilization 0.9 \
  --speculative-config '{"num_speculative_tokens": 3, "model":"Eco-Tech/GLM-4.7-W8A8-floatmtp", "method":"mtp"}' \
  --compilation-config '{"cudagraph_capture_sizes": [1,2,4,8,16,32,64,128,256,512], "cudagraph_mode": "FULL_DECODE_ONLY"}' \
  --additional-config '{"enable_shared_expert_dp": true, "ascend_fusion_config": {"fusion_ops_gmmswigluquant": false}}'\

Notice: The parameters are explained as follows:

• --async-scheduling Asynchronous scheduling is a technique used to optimize inference efficiency. It allows non-blocking task scheduling to improve concurrency and throughput, especially when processing large-scale models.
• fusion_ops_gmmswigluquant The performance of the GmmSwigluQuant fusion operator tends to degrade when the total number of NPUs is ≤ 16.

Multi-node Deployment

Although the former tutorial said "Not recommended to deploy multi-node on Atlas 800 A2 (64G × 8)", but if you insist to deploy GLM-4.x model on multi-node like 2 × Atlas 800 A2 (64G × 8), run the following scripts on two nodes respectively.

Node 0

#!/bin/sh

# this obtained through ifconfig
# nic_name is the network interface name corresponding to local_ip of the current node
nic_name="xxxx"
local_ip="xxxx"

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 HCCL_BUFFSIZE=512
export OMP_PROC_BIND=false
export OMP_NUM_THREADS=1
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export HCCL_OP_EXPANSION_MODE=AIV
export VLLM_ASCEND_BALANCE_SCHEDULING=1
export VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE=1
export VLLM_ASCEND_ENABLE_FLASHCOMM1=1
export VLLM_ASCEND_ENABLE_FUSED_MC2=1

vllm serve Eco-Tech/GLM-4.7-W8A8-floatmtp \
  --host 0.0.0.0 \
  --port 8004 \
  --data-parallel-size 2 \
  --data-parallel-size-local 1 \
  --data-parallel-start-rank 0 \
  --data-parallel-address $local_ip \
  --data-parallel-rpc-port 13389 \
  --tensor-parallel-size 8 \
  --enable-expert-parallel \
  --seed 1024 \
  --max-model-len 140000 \
  --max-num-batched-tokens 8192 \
  --max-num-seqs 16 \
  --async-scheduling \
  --quantization ascend \
  --trust-remote-code \
  --gpu-memory-utilization 0.9 \
  --enable-auto-tool-choice \
  --reasoning-parser glm45 \
  --tool-call-parser glm47 \
  --served-model-name glm47 \
  --speculative-config '{"num_speculative_tokens": 3, "model":"Eco-Tech/GLM-4.7-W8A8-floatmtp", "method":"mtp"}' \
  --compilation-config '{"cudagraph_capture_sizes": [1,2,4,8,16,32,64,128,256,512], "cudagraph_mode": "FULL_DECODE_ONLY"}' \
  --additional-config '{"enable_shared_expert_dp": true, "ascend_fusion_config": {"fusion_ops_gmmswigluquant": false}}'

Node 1

#!/bin/sh

# this obtained through ifconfig
# nic_name is the network interface name corresponding to local_ip of the current node
nic_name="xxxx"
local_ip="xxxx"
node0_ip="xxxx" # same as the local_IP address in node 0

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 HCCL_BUFFSIZE=512
export OMP_PROC_BIND=false
export OMP_NUM_THREADS=1
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export HCCL_OP_EXPANSION_MODE=AIV
export VLLM_ASCEND_BALANCE_SCHEDULING=1
export VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE=1
export VLLM_ASCEND_ENABLE_FLASHCOMM1=1
export VLLM_ASCEND_ENABLE_FUSED_MC2=1

vllm serve Eco-Tech/GLM-4.7-W8A8-floatmtp \
  --host 0.0.0.0 \
  --port 8004 \
  --headless \
  --data-parallel-size 2 \
  --data-parallel-size-local 1 \
  --data-parallel-start-rank 1 \
  --data-parallel-address $node0_ip \
  --data-parallel-rpc-port 13389 \
  --tensor-parallel-size 8 \
  --enable-expert-parallel \
  --seed 1024 \
  --max-model-len 140000 \
  --max-num-batched-tokens 8192 \
  --max-num-seqs 16 \
  --async-scheduling \
  --quantization ascend \
  --trust-remote-code \
  --gpu-memory-utilization 0.9 \
  --enable-auto-tool-choice \
  --reasoning-parser glm45 \
  --tool-call-parser glm47 \
  --served-model-name glm47 \
  --speculative-config '{"num_speculative_tokens": 3, "model":"Eco-Tech/GLM-4.7-W8A8-floatmtp", "method":"mtp"}' \
  --compilation-config '{"cudagraph_capture_sizes": [1,2,4,8,16,32,64,128,256,512], "cudagraph_mode": "FULL_DECODE_ONLY"}' \
  --additional-config '{"enable_shared_expert_dp": true, "ascend_fusion_config": {"fusion_ops_gmmswigluquant": false}}'

Prefill-Decode Disaggregation

We'd like to show the deployment guide of GLM4.7 on multi-node environment with 2P1D for better performance.

Before you start, please

1. prepare the script launch_online_dp.py on each node:

   import argparse
   import multiprocessing
   import os
   import subprocess
   import sys
   
   def parse_args():
       parser = argparse.ArgumentParser()
       parser.add_argument(
           "--dp-size",
           type=int,
           required=True,
           help="Data parallel size."
       )
       parser.add_argument(
           "--tp-size",
           type=int,
           default=1,
           help="Tensor parallel size."
       )
       parser.add_argument(
           "--dp-size-local",
           type=int,
           default=-1,
           help="Local data parallel size."
       )
       parser.add_argument(
           "--dp-rank-start",
           type=int,
           default=0,
           help="Starting rank for data parallel."
       )
       parser.add_argument(
           "--dp-address",
           type=str,
           required=True,
           help="IP address for data parallel master node."
       )
       parser.add_argument(
           "--dp-rpc-port",
           type=str,
           default=12345,
           help="Port for data parallel master node."
       )
       parser.add_argument(
           "--vllm-start-port",
           type=int,
           default=9000,
           help="Starting port for the engine."
       )
       return parser.parse_args()
   
   args = parse_args()
   dp_size = args.dp_size
   tp_size = args.tp_size
   dp_size_local = args.dp_size_local
   if dp_size_local == -1:
       dp_size_local = dp_size
   dp_rank_start = args.dp_rank_start
   dp_address = args.dp_address
   dp_rpc_port = args.dp_rpc_port
   vllm_start_port = args.vllm_start_port
   
   def run_command(visible_devices, dp_rank, vllm_engine_port):
       command = [
           "bash",
           "./run_dp_template.sh",
           visible_devices,
           str(vllm_engine_port),
           str(dp_size),
           str(dp_rank),
           dp_address,
           dp_rpc_port,
           str(tp_size),
       ]
       subprocess.run(command, check=True)
   
   if __name__ == "__main__":
       template_path = "./run_dp_template.sh"
       if not os.path.exists(template_path):
           print(f"Template file {template_path} does not exist.")
           sys.exit(1)
   
       processes = []
       num_cards = dp_size_local * tp_size
       for i in range(dp_size_local):
           dp_rank = dp_rank_start + i
           vllm_engine_port = vllm_start_port + i
           visible_devices = ",".join(str(x) for x in range(i * tp_size, (i + 1) * tp_size))
           process = multiprocessing.Process(target=run_command,
                                           args=(visible_devices, dp_rank,
                                                   vllm_engine_port))
           processes.append(process)
           process.start()
   
       for process in processes:
           process.join()
   
   

2. prepare the script run_dp_template.sh on each node.

   1. Prefill node 0

      nic_name="xxxx" # change to your own nic name
      local_ip="xxxx" # change to your own ip
      
      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 HCCL_BUFFSIZE=256
      export HCCL_OP_EXPANSION_MODE="AIV"
      export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
      export OMP_PROC_BIND=false
      export OMP_NUM_THREADS=1
      export ASCEND_AGGREGATE_ENABLE=1
      export ASCEND_TRANSPORT_PRINT=1
      export ACL_OP_INIT_MODE=1
      export ASCEND_A3_ENABLE=1
      export VLLM_ASCEND_BALANCE_SCHEDULING=1
      export VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE=1
      export VLLM_ASCEND_ENABLE_FLASHCOMM1=1
      export VLLM_ASCEND_ENABLE_FUSED_MC2=1
      export ASCEND_RT_VISIBLE_DEVICES=$1
      export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/mooncake:$LD_LIBRARY_PATH
      
      vllm serve Eco-Tech/GLM-4.7-W8A8-floatmtp \
          --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 \
          --seed 1024 \
          --served-model-name glm \
          --max-model-len 133000 \
          --max-num-batched-tokens 8192 \
          --trust-remote-code \
          --max-num-seqs 64 \
          --gpu-memory-utilization 0.9 \
          --quantization ascend \
          --enforce-eager \
          --speculative-config '{"num_speculative_tokens": 3, "model":"Eco-Tech/GLM-4.7-W8A8-floatmtp", "method":"mtp"}' \
          --profiler-config '{"profiler": "torch", "torch_profiler_dir": "./vllm_profile", "torch_profiler_with_stack": false}' \
          --additional-config '{"recompute_scheduler_enable": true, "enable_shared_expert_dp": true, "ascend_fusion_config": {"fusion_ops_gmmswigluquant": false}}' \
          --kv-transfer-config \
          '{"kv_connector": "MooncakeConnectorV1",
          "kv_role": "kv_producer",
          "kv_port": "30000",
          "engine_id": "0",
          "kv_connector_extra_config": {
                      "prefill": {
                              "dp_size": 2,
                              "tp_size": 8
                      },
                      "decode": {
                              "dp_size": 8,
                              "tp_size": 4
                      }
              }
          }' 2>&1
      
      

   2. Prefill node 1

      nic_name="xxxx" # change to your own nic name
      local_ip="xxxx" # change to your own ip
      
      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 HCCL_BUFFSIZE=256
      export HCCL_OP_EXPANSION_MODE="AIV"
      export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
      export OMP_PROC_BIND=false
      export OMP_NUM_THREADS=1
      export ASCEND_AGGREGATE_ENABLE=1
      export ASCEND_TRANSPORT_PRINT=1
      export ACL_OP_INIT_MODE=1
      export ASCEND_A3_ENABLE=1
      export VLLM_ASCEND_BALANCE_SCHEDULING=1
      export VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE=1
      export VLLM_ASCEND_ENABLE_FLASHCOMM1=1
      export VLLM_ASCEND_ENABLE_FUSED_MC2=1
      export ASCEND_RT_VISIBLE_DEVICES=$1
      export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/mooncake:$LD_LIBRARY_PATH
      
      vllm serve Eco-Tech/GLM-4.7-W8A8-floatmtp \
          --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 \
          --seed 1024 \
          --served-model-name glm \
          --max-model-len 133000 \
          --max-num-batched-tokens 8192 \
          --trust-remote-code \
          --max-num-seqs 64 \
          --gpu-memory-utilization 0.9 \
          --quantization ascend \
          --enforce-eager \
          --speculative-config '{"num_speculative_tokens": 3, "model":"Eco-Tech/GLM-4.7-W8A8-floatmtp", "method":"mtp"}' \
          --profiler-config '{"profiler": "torch", "torch_profiler_dir": "./vllm_profile", "torch_profiler_with_stack": false}' \
          --additional-config '{"recompute_scheduler_enable": true, "enable_shared_expert_dp": true, "ascend_fusion_config": {"fusion_ops_gmmswigluquant": false}}' \
          --kv-transfer-config \
          '{"kv_connector": "MooncakeConnectorV1",
          "kv_role": "kv_producer",
          "kv_port": "30000",
          "engine_id": "0",
          "kv_connector_extra_config": {
                      "prefill": {
                              "dp_size": 2,
                              "tp_size": 8
                      },
                      "decode": {
                              "dp_size": 8,
                              "tp_size": 4
                      }
              }
          }' 2>&1
      

   3. Decode node 0

      nic_name="xxxx" # change to your own nic name
      local_ip="xxxx" # change to your own ip
      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 HCCL_BUFFSIZE=512
      export HCCL_OP_EXPANSION_MODE="AIV"
      export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
      export OMP_PROC_BIND=false
      export OMP_NUM_THREADS=1
      export ASCEND_AGGREGATE_ENABLE=1
      export ASCEND_TRANSPORT_PRINT=1
      export ACL_OP_INIT_MODE=1
      export ASCEND_A3_ENABLE=1
      export VLLM_NIXL_ABORT_REQUEST_TIMEOUT=300000
      export TASK_QUEUE_ENABLE=1
      export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/mooncake:$LD_LIBRARY_PATH
      export VLLM_ASCEND_BALANCE_SCHEDULING=1
      export VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE=1
      export VLLM_ASCEND_ENABLE_FLASHCOMM1=1
      export VLLM_ASCEND_ENABLE_FUSED_MC2=1
      export ASCEND_RT_VISIBLE_DEVICES=$1
      
      vllm serve Eco-Tech/GLM-4.7-W8A8-floatmtp \
          --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 \
          --seed 1024 \
          --served-model-name glm \
          --max-model-len 133000 \
          --max-num-batched-tokens 128 \
          --max-num-seqs 4 \
          --trust-remote-code \
          --async-scheduling \
          --gpu-memory-utilization 0.9 \
          --quantization ascend \
          --speculative-config '{"num_speculative_tokens": 3, "model":"Eco-Tech/GLM-4.7-W8A8-floatmtp", "method":"mtp"}' \
          --profiler-config \
          '{"profiler": "torch",
          "torch_profiler_dir": "./vllm_profile",
          "torch_profiler_with_stack": false}' \
          --compilation-config '{"cudagraph_mode":"FULL_DECODE_ONLY",  "cudagraph_capture_sizes":[1,2,4,6,8,10,12,14,16,18,20,24,26,28,30,32,64,128,256,512]}' \
          --additional-config '{"recompute_scheduler_enable": true, "enable_shared_expert_dp": true, "ascend_fusion_config": {"fusion_ops_gmmswigluquant": false}}' \
          --kv-transfer-config \
          '{"kv_connector": "MooncakeConnectorV1",
          "kv_role": "kv_consumer",
          "kv_port": "30200",
          "engine_id": "2",
          "kv_connector_extra_config": {
                      "prefill": {
                              "dp_size": 2,
                              "tp_size": 8
                      },
                      "decode": {
                              "dp_size": 8,
                              "tp_size": 4
                      }
              }
          }' \
      

   4. Decode node 1

      nic_name="xxxx" # change to your own nic name
      local_ip="xxxx" # change to your own ip
      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 HCCL_BUFFSIZE=512
      export HCCL_OP_EXPANSION_MODE="AIV"
      export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
      export OMP_PROC_BIND=false
      export OMP_NUM_THREADS=1
      export ASCEND_AGGREGATE_ENABLE=1
      export ASCEND_TRANSPORT_PRINT=1
      export ACL_OP_INIT_MODE=1
      export ASCEND_A3_ENABLE=1
      export VLLM_NIXL_ABORT_REQUEST_TIMEOUT=300000
      export TASK_QUEUE_ENABLE=1
      export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/mooncake:$LD_LIBRARY_PATH
      export VLLM_ASCEND_BALANCE_SCHEDULING=1
      export VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE=1
      export VLLM_ASCEND_ENABLE_FLASHCOMM1=1
      export VLLM_ASCEND_ENABLE_FUSED_MC2=1
      export ASCEND_RT_VISIBLE_DEVICES=$1
      
      vllm serve Eco-Tech/GLM-4.7-W8A8-floatmtp \
          --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 \
          --seed 1024 \
          --served-model-name glm \
          --max-model-len 133000 \
          --max-num-batched-tokens 128 \
          --max-num-seqs 4 \
          --trust-remote-code \
          --async-scheduling \
          --gpu-memory-utilization 0.9 \
          --quantization ascend \
          --speculative-config '{"num_speculative_tokens": 3, "model":"Eco-Tech/GLM-4.7-W8A8-floatmtp", "method":"mtp"}' \
          --profiler-config \
          '{"profiler": "torch",
          "torch_profiler_dir": "./vllm_profile",
          "torch_profiler_with_stack": false}' \
          --compilation-config '{"cudagraph_mode":"FULL_DECODE_ONLY",  "cudagraph_capture_sizes":[1,2,4,6,8,10,12,14,16,18,20,24,26,28,30,32,64,128,256,512]}' \
          --additional-config '{"recompute_scheduler_enable": true, "enable_shared_expert_dp": true, "ascend_fusion_config": {"fusion_ops_gmmswigluquant": false}}' \
          --kv-transfer-config \
          '{"kv_connector": "MooncakeConnectorV1",
          "kv_role": "kv_consumer",
          "kv_port": "30200",
          "engine_id": "2",
          "kv_connector_extra_config": {
                      "prefill": {
                              "dp_size": 2,
                              "tp_size": 8
                      },
                      "decode": {
                              "dp_size": 8,
                              "tp_size": 4
                      }
              }
          }' \
      

Once the preparation is done, you can start the server with the following command on each node:

1. Prefill node 0

# change ip to your own
python launch_online_dp.py --dp-size 2 --tp-size 8 --dp-size-local 2 --dp-rank-start 0 --dp-address $node_p0_ip --dp-rpc-port 12880 --vllm-start-port 9300

2. Prefill node 1

# change ip to your own
python launch_online_dp.py --dp-size 2 --tp-size 8 --dp-size-local 2 --dp-rank-start 0 --dp-address $node_p1_ip --dp-rpc-port 12880 --vllm-start-port 9300

3. Decode node 0

# change ip to your own
python launch_online_dp.py --dp-size 8 --tp-size 4 --dp-size-local 4 --dp-rank-start 0 --dp-address $node_d0_ip --dp-rpc-port 12778 --vllm-start-port 9300

4. Decode node 1

# change ip to your own
python launch_online_dp.py --dp-size 8 --tp-size 4 --dp-size-local 4 --dp-rank-start 4 --dp-address $node_d0_ip --dp-rpc-port 12778 --vllm-start-port 9300

Request Forwarding

To set up request forwarding, run the following script on any machine. You can get the proxy program in the repository's examples: load_balance_proxy_server_example.py

unset http_proxy
unset https_proxy

python load_balance_proxy_server_example.py \
    --port 8000 \
    --host 0.0.0.0 \
    --prefiller-hosts \
       $node_p0_ip $node_p0_ip \
       $node_p1_ip $node_p1_ip \
    --prefiller-ports \
       9300 9301 \
       9300 9301 \
    --decoder-hosts \
      $node_d0_ip \
      $node_d0_ip \
      $node_d0_ip \
      $node_d0_ip \
      $node_d1_ip \
      $node_d1_ip \
      $node_d1_ip \
      $node_d1_ip \
    --decoder-ports \
      9300 9301 9302 9303 \
      9300 9301 9302 9303 \

Accuracy Evaluation

Here are two accuracy evaluation methods.

Using AISBench

1. Refer to Using AISBench for details.

2. After execution, you can get the result, here is the result of GLM4.7 in vllm-ascend:main (after vllm-ascend:0.14.0rc1) for reference only.

dataset	version	metric	mode	vllm-api-general-chat	note
GPQA	-	accuracy	gen	84.85	1 Atlas 800 A3 (64G × 16)
MATH500	-	accuracy	gen	98.8	1 Atlas 800 A3 (64G × 16)

Using Language Model Evaluation Harness

Not test yet.

Performance

Using AISBench

Refer to Using AISBench for performance evaluation for details.

Using vLLM Benchmark

Run performance evaluation of GLM-4.x as an example.

Refer to vllm benchmark for more details.

There are three vllm bench subcommands:

• latency: Benchmark the latency of a single batch of requests.
• serve: Benchmark the online serving throughput.
• throughput: Benchmark offline inference throughput.

Take the serve as an example. Run the code as follows.

vllm bench serve \
  --backend vllm \
  --dataset-name prefix_repetition \
  --prefix-repetition-prefix-len 22400 \
  --prefix-repetition-suffix-len 9600 \
  --prefix-repetition-output-len 1024 \
  --num-prompts 1 \
  --prefix-repetition-num-prefixes 1 \
  --ignore-eos \
  --model glm \
  --tokenizer Eco-Tech/GLM-4.7-W8A8-floatmtp \
  --seed 1000 \
  --host 0.0.0.0 \
  --port 8000 \
  --endpoint /v1/completions \
  --max-concurrency 1 \
  --request-rate 1 \

After about several minutes, you can get the performance evaluation result.