GLM-5

GLM-5#

Introduction#

GLM-5 use a Mixture-of-Experts (MoE) architecture and targeting at complex systems engineering and long-horizon agentic tasks.

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-5(BF16 version): Download model weight.
GLM-5-w4a8(Quantized version without MTP quant): Download model weight.
GLM-5-w4a8(Quantized version with MTP quant): Download model weight.
You can use msmodelslim to quantify the model naively.

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

Installation#

vLLM and vLLM-ascend only support GLM-5 on our main branches. you can use our glm5 docker images for inference.

A3 series

Start the docker image on your each node.

# Update --device according to your device (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, glm5-a3 can be replaced by: glm5;glm5-openeuler;glm5-a3-openeuler
export IMAGE=m.daocloud.io/quay.io/ascend/vllm-ascend:glm5-a3
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/davinci8 \
--device /dev/davinci9 \
--device /dev/davinci10 \
--device /dev/davinci11 \
--device /dev/davinci12 \
--device /dev/davinci13 \
--device /dev/davinci14 \
--device /dev/davinci15 \
--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

A2 series

Start the docker image on your each node.

export IMAGE=quay.io/ascend/vllm-ascend:glm5
docker run --rm \
    --name vllm-ascend \
    --shm-size=1g \
    --net=host \
    --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

In addition, if you don’t want to use the docker image as above, you can also build all from source:

Install vllm-ascend from source, refer to installation.
After install vllm-ascend from source, you should upgrade vllm、vllm-ascend、transformers to main branches:

# upgrade vllm
git clone https://github.com/vllm-project/vllm.git
cd vllm
git checkout 978a37c82387ce4a40aaadddcdbaf4a06fc4d590
VLLM_TARGET_DEVICE=empty pip install -v .

# upgrade vllm-ascend
git clone https://github.com/vllm-project/vllm-ascend.git
cd vllm-ascend
git checkout ff3a50d011dcbea08f87ebed69ff1bf156dbb01e
git submodule update --init --recursive
pip install -v .

# reinstall transformers
pip install git+https://github.com/huggingface/transformers.git

If you want to deploy multi-node environment, you need to set up environment on each node.

Deployment#

Single-node Deployment#

A3 series

Quantized model glm-5-w4a8 can be deployed on 1 Atlas 800 A3 (64G × 16) .

Run the following script to execute online inference.

export HCCL_OP_EXPANSION_MODE="AIV"
export OMP_PROC_BIND=false
export OMP_NUM_THREADS=10
export VLLM_USE_V1=1
export HCCL_BUFFSIZE=200
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export VLLM_ASCEND_BALANCE_SCHEDULING=1

vllm serve /root/.cache/modelscope/hub/models/vllm-ascend/GLM5-w4a8 \
--host 0.0.0.0 \
--port 8077 \
--data-parallel-size 1 \
--tensor-parallel-size 16 \
--enable-expert-parallel \
--seed 1024 \
--served-model-name glm-5 \
--max-num-seqs 8 \
--max-model-len 66600 \
--max-num-batched-tokens 4096 \
--trust-remote-code \
--gpu-memory-utilization 0.95 \
--quantization ascend \
--enable-chunked-prefill \
--enable-prefix-caching \
--async-scheduling \
--additional-config '{"multistream_overlap_shared_expert":true}' \
--compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}' \
--speculative-config '{"num_speculative_tokens": 3, "method": "deepseek_mtp"}' 

A2 series

Quantized model glm-5-w4a8 can be deployed on 1 Atlas 800 A2 (64G × 8) .

Run the following script to execute online inference.

export HCCL_OP_EXPANSION_MODE="AIV"
export OMP_PROC_BIND=false
export OMP_NUM_THREADS=10
export VLLM_USE_V1=1
export HCCL_BUFFSIZE=200
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export VLLM_ASCEND_BALANCE_SCHEDULING=1

vllm serve /root/.cache/modelscope/hub/models/vllm-ascend/GLM-5-w4a8 \
--host 0.0.0.0 \
--port 8077 \
--data-parallel-size 1 \
--tensor-parallel-size 8 \
--enable-expert-parallel \
--seed 1024 \
--served-model-name glm-5 \
--max-num-seqs 2 \
--max-model-len 32768 \
--max-num-batched-tokens 4096 \
--trust-remote-code \
--gpu-memory-utilization 0.95 \
--quantization ascend \
--enable-chunked-prefill \
--enable-prefix-caching \
--async-scheduling \
--compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}' \
--additional-config '{"multistream_overlap_shared_expert":true}' \
--speculative-config '{"num_speculative_tokens": 3, "method": "deepseek_mtp"}'

Notice: The parameters are explained as follows:

For single-node deployment, we recommend using dp1tp16 and turn off expert parallel in low-latency scenarios.
--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.

Multi-node Deployment#

If you want to deploy multi-node environment, you need to verify multi-node communication according to verify multi-node communication environment.

A3 series

glm-5-bf16: require at least 2 Atlas 800 A3 (64G × 16).

Run the following scripts on two nodes respectively.

node 0

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

# The value of node0_ip must be consistent with the value of local_ip set in node0 (master node)
node0_ip="xxxx"

export HCCL_OP_EXPANSION_MODE="AIV"

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 OMP_PROC_BIND=false
export OMP_NUM_THREADS=10
export VLLM_USE_V1=1
export HCCL_BUFFSIZE=200
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True

vllm serve /root/.cache/modelscope/hub/models/vllm-ascend/GLM5-bf16 \
--host 0.0.0.0 \
--port 8077 \
--data-parallel-size 2 \
--data-parallel-size-local 1 \
--data-parallel-address $node0_ip \
--data-parallel-rpc-port 12890 \
--tensor-parallel-size 16 \
--seed 1024 \
--served-model-name glm-5 \
--enable-expert-parallel \
--max-num-seqs 16 \
--max-model-len 8192 \
--max-num-batched-tokens 4096 \
--trust-remote-code \
--no-enable-prefix-caching \
--gpu-memory-utilization 0.95 \
--compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}' \
--speculative-config '{"num_speculative_tokens": 3, "method": "deepseek_mtp"}'

node 1

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

# The value of node0_ip must be consistent with the value of local_ip set in node0 (master node)
node0_ip="xxxx"

export HCCL_OP_EXPANSION_MODE="AIV"

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 OMP_PROC_BIND=false
export OMP_NUM_THREADS=10
export VLLM_USE_V1=1
export HCCL_BUFFSIZE=200
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True

vllm serve /root/.cache/modelscope/hub/models/vllm-ascend/GLM5-bf16 \
--host 0.0.0.0 \
--port 8077 \
--headless \
--data-parallel-size 2 \
--data-parallel-size-local 1 \
--data-parallel-start-rank 1 \
--data-parallel-address $node0_ip \
--data-parallel-rpc-port 12890 \
--tensor-parallel-size 16 \
--seed 1024 \
--served-model-name glm-5 \
--enable-expert-parallel \
--max-num-seqs 16 \
--max-model-len 8192 \
--max-num-batched-tokens 4096 \
--trust-remote-code \
--no-enable-prefix-caching \
--gpu-memory-utilization 0.95 \
--compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}' \
--speculative-config '{"num_speculative_tokens": 3, "method": "deepseek_mtp"}'

A2 series

Run the following scripts on two nodes respectively.

node 0

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

# The value of node0_ip must be consistent with the value of local_ip set in node0 (master node)
node0_ip="xxx"

export HCCL_OP_EXPANSION_MODE="AIV"

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 OMP_PROC_BIND=false
export OMP_NUM_THREADS=10
export VLLM_USE_V1=1
export HCCL_BUFFSIZE=200
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True

vllm serve /root/.cache/modelscope/hub/models/vllm-ascend/GLM-5-w4a8 \
--host 0.0.0.0 \
--port 8077 \
--data-parallel-size 2 \
--data-parallel-size-local 1 \
--data-parallel-address $node0_ip \
--data-parallel-rpc-port 13389 \
--tensor-parallel-size 8 \
--quantization ascend \
--seed 1024 \
--served-model-name glm-5 \
--enable-expert-parallel \
--max-num-seqs 2 \
--max-model-len 131072 \
--max-num-batched-tokens 4096 \
--trust-remote-code \
--no-enable-prefix-caching \
--gpu-memory-utilization 0.95 \
--compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}' \
--additional-config '{"multistream_overlap_shared_expert":true}' \
--speculative-config '{"num_speculative_tokens": 3, "method": "deepseek_mtp"}'

node 1

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

# The value of node0_ip must be consistent with the value of local_ip set in node0 (master node)
node0_ip="xxx"

export HCCL_OP_EXPANSION_MODE="AIV"

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 OMP_PROC_BIND=false
export OMP_NUM_THREADS=10
export VLLM_USE_V1=1
export HCCL_BUFFSIZE=200
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True

vllm serve /root/.cache/modelscope/hub/models/vllm-ascend/GLM-5-w4a8 \
--host 0.0.0.0 \
--port 8077 \
--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 \
--quantization ascend \
--seed 1024 \
--served-model-name glm-5 \
--enable-expert-parallel \
--max-num-seqs 2 \
--max-model-len 131072 \
--max-num-batched-tokens 4096 \
--trust-remote-code \
--no-enable-prefix-caching \
--gpu-memory-utilization 0.95 \
--compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}' \
--additional-config '{"multistream_overlap_shared_expert":true}' \
--speculative-config '{"num_speculative_tokens": 3, "method": "deepseek_mtp"}'

For bf16 weight, use this script on each node to enable Multi Token Prediction (MTP).

python adjust_weight.py "path_of_bf16_weight"

# adjust_weight.py
from safetensors.torch import safe_open, save_file
import torch
import json
import os
import sys

target_keys = ["model.embed_tokens.weight", "lm_head.weight"]

def get_tensor_info(file_path):
   with safe_open(file_path, framework="pt", device="cpu") as f:
         tensor_names = f.keys()
         tensor_dict = {}
         for name in tensor_names:
            tensor = f.get_tensor(name)
            tensor_dict[name] = tensor
         return tensor_dict


if __name__ == "__main__":
   directory_path = sys.argv[1]
   json_name = "model.safetensors.index.json"
   json_path = os.path.join(directory_path, json_name)
   with open(json_path, 'r', encoding='utf-8') as f:
         json_data = json.load(f)
   weight_map = json_data.get('weight_map', {})
   file_list = []
   for key in target_keys:
         safetensor_file = weight_map.get(key)
         file_list.append(directory_path + safetensor_file)

   new_dict = {}
   for file_path in file_list:
         tensor_dict = get_tensor_info(file_path)
         for key in target_keys:
            if key in tensor_dict:
               if key == "model.embed_tokens.weight":
                     new_key = "model.layers.78.embed_tokens.weight"
               elif key == "lm_head.weight":
                     new_key = "model.layers.78.shared_head.head.weight"
               new_dict[new_key] = tensor_dict[key]

   new_file_name = os.path.join(directory_path, "mtp-others.safetensors")
   new_key = ["model.layers.78.embed_tokens.weight", "model.layers.78.shared_head.head.weight"]
   save_file(tensors=new_dict, filename=new_file_name)
   for key in new_key:
         json_data["weight_map"][key] = "mtp-others.safetensors"
   with open(json_path, 'w', encoding='utf-8') as f:
         json.dump(json_data, f, indent=2)

Prefill-Decode Disaggregation#

Not test yet.

Accuracy Evaluation#

Here are two accuracy evaluation methods.

Using AISBench#

Refer to Using AISBench for details.
After execution, you can get the result.

Using Language Model Evaluation Harness#

Not test yet.

Performance#

Using AISBench#

Refer to Using AISBench for performance evaluation for details.

Using vLLM Benchmark#

Refer to vllm benchmark for more details.

GLM-5

Contents

GLM-5#

Introduction#

Supported Features#

Environment Preparation#

Model Weight#

Installation#

Deployment#

Single-node Deployment#

Multi-node Deployment#

Prefill-Decode Disaggregation#

Accuracy Evaluation#

Using AISBench#

Using Language Model Evaluation Harness#

Performance#

Using AISBench#

Using vLLM Benchmark#