[doc] add Prefill-Decode Disaggregation doc for GLM5.md (#7300)

### What this PR does / why we need it?
add Prefill-Decode Disaggregation doc for GLM5.md
w8a8  65k-1.5k 
Concurrency: 80 
prefixcache: 90%
tps: 2054

- vLLM version: v0.17.0

- vLLM main:
4034c3d32e
---------
Signed-off-by: liuhaiyang27 <liuhaiyang27@huawei.com>
Co-authored-by: liuhaiyang27 <liuhaiyang27@huawei.com>

docs/source/tutorials/models/GLM5.md

@@ -17,15 +17,15 @@ Refer to [feature guide](../../user_guide/feature_guide/index.md) to get the fea
 ### Model Weight
 
 - `GLM-5`(BF16 version): [Download model weight](https://www.modelscope.cn/models/ZhipuAI/GLM-5).
-- `GLM-5-w4a8`(Quantized version without MTP quant): [Download model weight](https://modelscope.cn/models/Eco-Tech/GLM-5-w4a8).
+- `GLM-5-w4a8`: [Download model weight](https://modelscope.cn/models/Eco-Tech/GLM-5-w4a8).
-- `GLM-5-w4a8`(Quantized version with MTP quant): [Download model weight](https://modelscope.cn/models/Eco-Tech/GLM-5-w4a8-mtp-QuaRot).
+- `GLM-5-w8a8`: [Download model weight](https://ai.gitcode.com/Eco-Tech/GLM-5-w8a8/tree/main).
 - You can use [msmodelslim](https://gitcode.com/Ascend/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.
+You can use our official docker image to run GLM-5 directly.
 
 :::::{tab-set}
 :sync-group: install
@@ -38,11 +38,7 @@ Start the docker image on your each node.
 ```{code-block} bash
    :substitutions:
 
-# Update --device according to your device (Atlas A3:/dev/davinci[0-15]).
+export IMAGE=quay.io/ascend/vllm-ascend:|vllm_ascend_version|-a3
-# 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
@@ -89,7 +85,7 @@ Start the docker image on your each node.
 ```{code-block} bash
    :substitutions:
 
-export IMAGE=quay.io/ascend/vllm-ascend:glm5
+export IMAGE=quay.io/ascend/vllm-ascend:|vllm_ascend_version|
 docker run --rm \
     --name vllm-ascend \
     --shm-size=1g \
@@ -122,26 +118,6 @@ In addition, if you don't want to use the docker image as above, you can also bu
 
 - Install `vllm-ascend` from source, refer to [installation](https://docs.vllm.ai/projects/ascend/en/latest/installation.html).
 
-- After install `vllm-ascend`  from source, you should upgrade vllm、vllm-ascend、transformers to main branches:
-
-```shell
-# 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
@@ -162,8 +138,7 @@ Run the following script to execute online inference.
    :substitutions:
 export HCCL_OP_EXPANSION_MODE="AIV"
 export OMP_PROC_BIND=false
-export OMP_NUM_THREADS=10
+export OMP_NUM_THREADS=1
-export VLLM_USE_V1=1
 export HCCL_BUFFSIZE=200
 export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
 export VLLM_ASCEND_BALANCE_SCHEDULING=1
@@ -185,7 +160,43 @@ vllm serve /root/.cache/modelscope/hub/models/vllm-ascend/GLM5-w4a8 \
 --enable-chunked-prefill \
 --enable-prefix-caching \
 --async-scheduling \
---additional-config '{"multistream_overlap_shared_expert":true}' \
+--additional-config '{"enable_npugraph_ex": true,"fuse_muls_add":true,"multistream_overlap_shared_expert":true}' \
+--compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}' \
+--speculative-config '{"num_speculative_tokens": 3, "method": "deepseek_mtp"}' 
+```
+
+- Quantized model `glm-5-w8a8` can be deployed on 1 Atlas 800 A3 (64G × 16) .
+
+Run the following script to execute online inference.
+
+```{code-block} bash
+   :substitutions:
+export HCCL_OP_EXPANSION_MODE="AIV"
+export OMP_PROC_BIND=false
+export OMP_NUM_THREADS=1
+export HCCL_BUFFSIZE=200
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export VLLM_ASCEND_BALANCE_SCHEDULING=1
+export VLLM_ASCEND_ENABLE_MLAPO=1
+
+vllm serve /root/.cache/modelscope/hub/models/vllm-ascend/GLM5-w8a8 \
+--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 40960 \
+--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 '{"enable_npugraph_ex": true,"fuse_muls_add":true,"multistream_overlap_shared_expert":true}' \
 --compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}' \
 --speculative-config '{"num_speculative_tokens": 3, "method": "deepseek_mtp"}' 
 ```
@@ -202,8 +213,7 @@ Run the following script to execute online inference.
    :substitutions:
 export HCCL_OP_EXPANSION_MODE="AIV"
 export OMP_PROC_BIND=false
-export OMP_NUM_THREADS=10
+export OMP_NUM_THREADS=1
-export VLLM_USE_V1=1
 export HCCL_BUFFSIZE=200
 export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
 export VLLM_ASCEND_BALANCE_SCHEDULING=1
@@ -226,7 +236,7 @@ vllm serve /root/.cache/modelscope/hub/models/vllm-ascend/GLM-5-w4a8 \
 --enable-prefix-caching \
 --async-scheduling \
 --compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}' \
---additional-config '{"multistream_overlap_shared_expert":true}' \
+--additional-config '{"enable_npugraph_ex": true,"fuse_muls_add":true,"multistream_overlap_shared_expert":true}' \
 --speculative-config '{"num_speculative_tokens": 3, "method": "deepseek_mtp"}'
 ```
 
@@ -272,8 +282,7 @@ 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 OMP_NUM_THREADS=1
-export VLLM_USE_V1=1
 export HCCL_BUFFSIZE=200
 export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
 
@@ -317,8 +326,7 @@ 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 OMP_NUM_THREADS=1
-export VLLM_USE_V1=1
 export HCCL_BUFFSIZE=200
 export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
 
@@ -370,8 +378,7 @@ 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 OMP_NUM_THREADS=1
-export VLLM_USE_V1=1
 export HCCL_BUFFSIZE=200
 export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
 
@@ -394,7 +401,7 @@ vllm serve /root/.cache/modelscope/hub/models/vllm-ascend/GLM-5-w4a8 \
 --no-enable-prefix-caching \
 --gpu-memory-utilization 0.95 \
 --compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}' \
---additional-config '{"multistream_overlap_shared_expert":true}' \
+--additional-config '{"enable_npugraph_ex": true, "fuse_muls_add":true,"multistream_overlap_shared_expert":true}' \
 --speculative-config '{"num_speculative_tokens": 3, "method": "deepseek_mtp"}'
 ```
 
@@ -417,8 +424,7 @@ 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 OMP_NUM_THREADS=1
-export VLLM_USE_V1=1
 export HCCL_BUFFSIZE=200
 export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
 
@@ -443,7 +449,7 @@ vllm serve /root/.cache/modelscope/hub/models/vllm-ascend/GLM-5-w4a8 \
 --no-enable-prefix-caching \
 --gpu-memory-utilization 0.95 \
 --compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}' \
---additional-config '{"multistream_overlap_shared_expert":true}' \
+--additional-config '{"enable_npugraph_ex": true, "fuse_muls_add":true,"multistream_overlap_shared_expert":true}' \
 --speculative-config '{"num_speculative_tokens": 3, "method": "deepseek_mtp"}'
 ```
 
@@ -508,9 +514,799 @@ if __name__ == "__main__":
          json.dump(json_data, f, indent=2)
 ```
 
+:::::{tab-set}
+:sync-group: install
+
+::::{tab-item} A3 series
+:sync: A3
+
+- `glm-5-w8a8`: require 2 Atlas 800 A3 (64G × 16).
+
+Run the following scripts on two nodes respectively.
+
+**node 0**
+
+```{code-block} bash
+   :substitutions:
+# 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=1
+export HCCL_BUFFSIZE=200
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export VLLM_ASCEND_ENABLE_MLAPO=1
+
+vllm serve /root/.cache/modelscope/hub/models/vllm-ascend/GLM5-w8a8 \
+--host 0.0.0.0 \
+--port 8077 \
+--data-parallel-size 2 \
+--data-parallel-size-local 1 \
+--data-parallel-address $node0_ip \
+--data-parallel-rpc-port 12890 \
+--tensor-parallel-size 16 \
+--seed 1024 \
+--served-model-name glm-5 \
+--enable-expert-parallel \
+--max-num-seqs 16 \
+--max-model-len 65536 \
+--max-num-batched-tokens 4096 \
+--trust-remote-code \
+--gpu-memory-utilization 0.95 \
+--quantization ascend \
+--enable-chunked-prefill \
+--enable-prefix-caching \
+--async-scheduling \
+--compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}' \
+--additional-config '{"enable_npugraph_ex": true,"fuse_muls_add":true,"multistream_overlap_shared_expert":true}' \
+--speculative-config '{"num_speculative_tokens": 3, "method": "deepseek_mtp"}'
+```
+
+**node 1**
+
+```{code-block} bash
+   :substitutions:
+# this obtained through ifconfig
+# nic_name is the network interface name corresponding to local_ip of the current node
+nic_name="xxx"
+local_ip="xxx"
+
+# The value of node0_ip must be consistent with the value of local_ip set in node0 (master node)
+node0_ip="xxxx"
+
+export HCCL_OP_EXPANSION_MODE="AIV"
+
+export HCCL_IF_IP=$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=1
+export HCCL_BUFFSIZE=200
+export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+export VLLM_ASCEND_ENABLE_MLAPO=1
+
+vllm serve /root/.cache/modelscope/hub/models/vllm-ascend/GLM5-w8a8 \
+--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 65536 \
+--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 '{"enable_npugraph_ex": true,"fuse_muls_add":true,"multistream_overlap_shared_expert":true}' \
+--speculative-config '{"num_speculative_tokens": 3, "method": "deepseek_mtp"}'
+```
+
+::::
+:::::
+
 ### Prefill-Decode Disaggregation
 
-Not test yet.
+We'd like to show the deployment guide of `GLM-5` on multi-node environment with 1P1D for better performance.
+
+Before you start, please
+
+1. prepare the script `launch_online_dp.py` on each node:
+
+    ```python
+    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
+
+        ```shell
+        nic_name="xxxx" # change to your own nic name
+        local_ip="xxxx" # change to your own ip
+
+        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=1
+        export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+        export HCCL_BUFFSIZE=256
+
+        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 ASCEND_RT_VISIBLE_DEVICES=$1
+
+        export VLLM_ASCEND_ENABLE_FLASHCOMM1=1
+          
+        export VLLM_ASCEND_ENABLE_FUSED_MC2=1
+        export VLLM_ASCEND_ENABLE_MLAPO=1
+        export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib
+
+        vllm serve /root/.cache/glm5-w8a8 \
+            --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 $7 \
+            --enable-expert-parallel \
+            --speculative-config '{"num_speculative_tokens": 3, "method":"deepseek_mtp"}' \
+            --profiler-config \
+            '{"profiler": "torch",
+            "torch_profiler_dir": "./vllm_profile",
+            "torch_profiler_with_stack": false}' \
+            --seed 1024 \
+            --served-model-name glm-5 \
+            --max-model-len 131072 \
+            --additional-config '{"enable_npugraph_ex": true, "fuse_muls_add":true,"multistream_overlap_shared_expert":true,"recompute_scheduler_enable" : true}' \
+            --max-num-batched-tokens 4096 \
+            --trust-remote-code \
+            --max-num-seqs 64 \
+            --quantization ascend \
+            --gpu-memory-utilization 0.95 \
+            --enforce-eager \
+            --enable-auto-tool-choice \
+            --tool-call-parser glm47 \
+            --reasoning-parser glm45 \
+            --kv-transfer-config \
+            '{"kv_connector": "MooncakeConnectorV1",
+            "kv_role": "kv_producer",
+            "kv_port": "30000",
+            "engine_id": "0",
+            "kv_connector_extra_config": {
+                        "use_ascend_direct": true,
+                        "prefill": {
+                                "dp_size": 4,
+                                "tp_size": 8
+                        },
+                        "decode": {
+                                "dp_size": 16,
+                                "tp_size": 4
+                        }
+                }
+            }'
+
+        ```
+
+    2. Prefill node 1
+
+        ```shell
+        nic_name="xxxx" # change to your own nic name
+        local_ip="xxxx" # change to your own ip
+
+        export HCCL_OP_EXPANSION_MODE="AIV"
+
+        export HCCL_IF_IP=$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=1
+        export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+        export HCCL_BUFFSIZE=256
+
+        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 ASCEND_RT_VISIBLE_DEVICES=$1
+        export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+
+        export VLLM_ASCEND_ENABLE_FLASHCOMM1=1
+       
+        export VLLM_ASCEND_ENABLE_FUSED_MC2=1
+        export VLLM_ASCEND_ENABLE_MLAPO=1
+        export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib
+
+        vllm serve /root/.cache/glm5-w8a8 \
+            --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 $7 \
+            --enable-expert-parallel \
+            --speculative-config '{"num_speculative_tokens": 3, "method":"deepseek_mtp"}' \
+            --profiler-config \
+            '{"profiler": "torch",
+            "torch_profiler_dir": "./vllm_profile",
+            "torch_profiler_with_stack": false}' \
+            --seed 1024 \
+            --served-model-name glm-5 \
+            --max-model-len 131072 \
+            --additional-config '{"enable_npugraph_ex": true, "fuse_muls_add":true,"multistream_overlap_shared_expert":true,"recompute_scheduler_enable" : true}' \
+            --max-num-batched-tokens 4096 \
+            --trust-remote-code \
+            --max-num-seqs 64 \
+            --gpu-memory-utilization 0.95 \
+            --quantization ascend \
+            --enforce-eager \
+            --enable-auto-tool-choice \
+            --tool-call-parser glm47 \
+            --reasoning-parser glm45 \
+            --kv-transfer-config \
+            '{"kv_connector": "MooncakeConnectorV1",
+            "kv_role": "kv_producer",
+            "kv_port": "30000",
+            "engine_id": "0",
+            "kv_connector_extra_config": {
+                        "use_ascend_direct": true,
+                        "prefill": {
+                                "dp_size": 4,
+                                "tp_size": 8
+                        },
+                        "decode": {
+                                "dp_size": 16,
+                                "tp_size": 4
+                        }
+                }
+            }'
+        ```
+
+    3. Decode node 0
+
+        ```shell
+        nic_name="xxxx" # change to your own nic name
+        local_ip="xxxx" # change to your own ip
+    
+        export HCCL_OP_EXPANSION_MODE="AIV"
+    
+        export HCCL_IF_IP=$local_ip
+        export GLOO_SOCKET_IFNAME=$nic_name
+        export TP_SOCKET_IFNAME=$nic_name
+        export HCCL_SOCKET_IFNAME=$nic_name
+    
+        #Mooncake
+        export OMP_PROC_BIND=false
+        export OMP_NUM_THREADS=1
+    
+        export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+        export HCCL_BUFFSIZE=256
+    
+    
+        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 ASCEND_RT_VISIBLE_DEVICES=$1
+          
+        export VLLM_ASCEND_ENABLE_FUSED_MC2=1
+        export VLLM_ASCEND_ENABLE_MLAPO=1
+        export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib
+    
+        vllm serve /root/.cache/glm5-w8a8 \
+            --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 $7 \
+            --enable-expert-parallel \
+            --speculative-config '{"num_speculative_tokens": 3,  "method":"deepseek_mtp"}' \
+            --profiler-config \
+            '{"profiler": "torch",
+            "torch_profiler_dir": "./vllm_profile",
+            "torch_profiler_with_stack": false}' \
+            --seed 1024 \
+            --served-model-name glm-5 \
+            --max-model-len 200000 \
+            --max-num-batched-tokens 32 \
+            --compilation-config '{"cudagraph_mode":"FULL_DECODE_ONLY", "cudagraph_capture_sizes":[4, 8, 12, 16,20,24,28, 32]}' \
+            --additional-config '{"enable_npugraph_ex": true, "fuse_muls_add":true,"multistream_overlap_shared_expert":true,"recompute_scheduler_enable" : true}' \
+            --trust-remote-code \
+            --max-num-seqs 8 \
+            --gpu-memory-utilization 0.92 \
+            --async-scheduling \
+            --quantization ascend \
+            --enable-auto-tool-choice \
+            --tool-call-parser glm47 \
+            --reasoning-parser glm45 \
+            --kv-transfer-config \
+            '{"kv_connector": "MooncakeConnectorV1",
+            "kv_role": "kv_consumer",
+            "kv_port": "30100",
+            "engine_id": "1",
+            "kv_connector_extra_config": {
+                        "use_ascend_direct": true,
+                        "prefill": {
+                                "dp_size": 4,
+                                "tp_size": 8
+                        },
+                        "decode": {
+                                "dp_size": 16,
+                                "tp_size": 4
+                        }
+                }
+            }'
+        ```
+
+    4. Decode node 1
+
+         ```shell
+         nic_name="xxxx" # change to your own nic name
+         local_ip="xxxx" # change to your own ip
+            
+         export HCCL_OP_EXPANSION_MODE="AIV"
+            
+         export HCCL_IF_IP=$local_ip
+         export GLOO_SOCKET_IFNAME=$nic_name
+         export TP_SOCKET_IFNAME=$nic_name
+         export HCCL_SOCKET_IFNAME=$nic_name
+            
+         #Mooncake
+         export OMP_PROC_BIND=false
+         export OMP_NUM_THREADS=1
+            
+         export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+         export HCCL_BUFFSIZE=256
+            
+         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 ASCEND_RT_VISIBLE_DEVICES=$1
+                     
+         export VLLM_ASCEND_ENABLE_FUSED_MC2=1
+         export VLLM_ASCEND_ENABLE_MLAPO=1
+         export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib
+            
+         vllm serve /root/.cache/glm5-w8a8 \
+             --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 \
+             --speculative-config '{"num_speculative_tokens": 3,  "method":"deepseek_mtp"}' \
+             --profiler-config \
+             '{"profiler": "torch",
+             "torch_profiler_dir": "./vllm_profile",
+             "torch_profiler_with_stack": false}' \
+             --seed 1024 \
+             --served-model-name glm-5 \
+             --max-model-len 200000 \
+             --max-num-batched-tokens 32 \
+             --compilation-config '{"cudagraph_mode":"FULL_DECODE_ONLY", "cudagraph_capture_sizes":[4, 8, 12, 16,20,24,28, 32]}' \
+             --additional-config '{"enable_npugraph_ex": true, "fuse_muls_add":true,"multistream_overlap_shared_expert":true,"recompute_scheduler_enable" : true}' \
+             --trust-remote-code \
+             --max-num-seqs 8 \
+             --gpu-memory-utilization 0.92 \
+             --async-scheduling \
+             --quantization ascend \
+             --enable-auto-tool-choice \
+             --tool-call-parser glm47 \
+             --reasoning-parser glm45 \
+             --kv-transfer-config \
+             '{"kv_connector": "MooncakeConnectorV1",
+             "kv_role": "kv_consumer",
+             "kv_port": "30100",
+             "engine_id": "1",
+             "kv_connector_extra_config": {
+                         "use_ascend_direct": true,
+                         "prefill": {
+                                 "dp_size": 4,
+                                 "tp_size": 8
+                         },
+                         "decode": {
+                                 "dp_size": 16,
+                                 "tp_size": 4
+                         }
+                 }
+             }'
+         ```
+
+    5. Decode node 2
+
+         ```shell
+         nic_name="xxxx" # change to your own nic name
+         local_ip="xxxx" # change to your own ip
+            
+         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
+            
+         #Mooncake
+         export OMP_PROC_BIND=false
+         export OMP_NUM_THREADS=1
+            
+         export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+         export HCCL_BUFFSIZE=256
+            
+         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 ASCEND_RT_VISIBLE_DEVICES=$1
+                     
+         export VLLM_ASCEND_ENABLE_FUSED_MC2=1
+         export VLLM_ASCEND_ENABLE_MLAPO=1
+         export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib
+            
+         vllm serve /root/.cache/glm5-w8a8 \
+             --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 \
+             --speculative-config '{"num_speculative_tokens": 3,  "method":"deepseek_mtp"}' \
+             --profiler-config \
+             '{"profiler": "torch",
+             "torch_profiler_dir": "./vllm_profile",
+             "torch_profiler_with_stack": false}' \
+             --seed 1024 \
+             --served-model-name glm-5 \
+             --max-model-len 200000 \
+             --max-num-batched-tokens 32 \
+             --compilation-config '{"cudagraph_mode":"FULL_DECODE_ONLY", "cudagraph_capture_sizes":[4, 8, 12, 16,20,24,28, 32]}' \
+             --additional-config '{"enable_npugraph_ex": true, "fuse_muls_add":true,"multistream_overlap_shared_expert":true,"recompute_scheduler_enable" : true}' \
+             --trust-remote-code \
+             --max-num-seqs 8 \
+             --gpu-memory-utilization 0.92 \
+             --async-scheduling \
+             --quantization ascend \
+             --enable-auto-tool-choice \
+             --tool-call-parser glm47 \
+             --reasoning-parser glm45 \
+             --kv-transfer-config \
+             '{"kv_connector": "MooncakeConnectorV1",
+             "kv_role": "kv_consumer",
+             "kv_port": "30100",
+             "engine_id": "1",
+             "kv_connector_extra_config": {
+                         "use_ascend_direct": true,
+                         "prefill": {
+                                 "dp_size": 4,
+                                 "tp_size": 8
+                         },
+                         "decode": {
+                                 "dp_size": 16,
+                                 "tp_size": 4
+                         }
+                 }
+             }'
+         ```
+
+    6. Decode node 3
+
+         ```shell
+         nic_name="xxxx" # change to your own nic name
+         local_ip="xxxx" # change to your own ip
+            
+         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
+            
+         #Mooncake
+         export OMP_PROC_BIND=false
+         export OMP_NUM_THREADS=1
+            
+         export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
+         export HCCL_BUFFSIZE=256
+            
+         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 ASCEND_RT_VISIBLE_DEVICES=$1
+                     
+         export VLLM_ASCEND_ENABLE_FUSED_MC2=1
+         export VLLM_ASCEND_ENABLE_MLAPO=1
+         export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib
+            
+         vllm serve /root/.cache/glm5-w8a8 \
+             --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 \
+             --speculative-config '{"num_speculative_tokens": 3,  "method":"deepseek_mtp"}' \
+             --profiler-config \
+             '{"profiler": "torch",
+             "torch_profiler_dir": "./vllm_profile",
+             "torch_profiler_with_stack": false}' \
+             --seed 1024 \
+             --served-model-name glm-5 \
+             --max-model-len 200000 \
+             --max-num-batched-tokens 32 \
+             --compilation-config '{"cudagraph_mode":"FULL_DECODE_ONLY", "cudagraph_capture_sizes":[4, 8, 12, 16,20,24,28, 32]}' \
+             --additional-config '{"enable_npugraph_ex": true, "fuse_muls_add":true,"multistream_overlap_shared_expert":true,"recompute_scheduler_enable" : true}' \
+             --trust-remote-code \
+             --max-num-seqs 8 \
+             --gpu-memory-utilization 0.92 \
+             --async-scheduling \
+             --quantization ascend \
+             --enable-auto-tool-choice \
+             --tool-call-parser glm47 \
+             --reasoning-parser glm45 \
+             --kv-transfer-config \
+             '{"kv_connector": "MooncakeConnectorV1",
+             "kv_role": "kv_consumer",
+             "kv_port": "30100",
+             "engine_id": "1",
+             "kv_connector_extra_config": {
+                         "use_ascend_direct": true,
+                         "prefill": {
+                                 "dp_size": 4,
+                                 "tp_size": 8
+                         },
+                         "decode": {
+                                 "dp_size": 16,
+                                 "tp_size": 4
+                         }
+                 }
+             }'
+         ```
+
+Once the preparation is done, you can start the server with the following command on each node:
+
+1. Prefill node 0
+
+```shell
+# change ip to your own
+python launch_online_dp.py --dp-size 4 --tp-size 8 --dp-size-local 2 --dp-rank-start 0 --dp-address $node_p0_ip --dp-rpc-port 10521 --vllm-start-port 6700
+```
+
+2. Prefill node 1
+
+```shell
+# change ip to your own
+python launch_online_dp.py --dp-size 4 --tp-size 8 --dp-size-local 2 --dp-rank-start 2 --dp-address $node_p0_ip --dp-rpc-port 10521 --vllm-start-port 6700
+```
+
+3. Decode node 0
+
+```shell
+# change ip to your own
+python launch_online_dp.py --dp-size 16 --tp-size 4 --dp-size-local 4 --dp-rank-start 0 --dp-address $node_d0_ip --dp-rpc-port 10523 --vllm-start-port 6721
+```
+
+4. Decode node 1
+
+```shell
+# change ip to your own
+python launch_online_dp.py --dp-size 16 --tp-size 4 --dp-size-local 4 --dp-rank-start 4 --dp-address $node_d0_ip --dp-rpc-port 10523 --vllm-start-port 6721
+```
+
+5. Decode node 2
+
+```shell
+# change ip to your own
+python launch_online_dp.py --dp-size 16 --tp-size 4 --dp-size-local 4 --dp-rank-start 8 --dp-address $node_d0_ip --dp-rpc-port 10523 --vllm-start-port 6721
+```
+
+6. Decode node 3
+
+```shell
+# change ip to your own
+python launch_online_dp.py --dp-size 16 --tp-size 4 --dp-size-local 4 --dp-rank-start 12 --dp-address $node_d0_ip --dp-rpc-port 10523 --vllm-start-port 6721
+```
+
+### 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](https://github.com/vllm-project/vllm-ascend/blob/main/examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py)
+
+```shell
+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 \
+       6700 6701 \
+       6700 6701 \
+    --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 \
+      $node_d2_ip \
+      $node_d2_ip \
+      $node_d2_ip \
+      $node_d2_ip \
+      $node_d3_ip \
+      $node_d3_ip \
+      $node_d3_ip \
+      $node_d3_ip \
+    --decoder-ports \
+      6721 6722 6723 6724 \
+      6721 6722 6723 6724 \
+      6721 6722 6723 6724 \
+      6721 6722 6723 6724      
+```
 
 ## Accuracy Evaluation
 

docs/source/user_guide/release_notes.md

@@ -17,7 +17,7 @@ This is the first release candidate of v0.17.0 for vLLM Ascend. Please follow th
 - FlashLB algorithm for EPLB: supports per-step heat collection and multi-stage load balancing for better expert parallelism efficiency. [#6477](https://github.com/vllm-project/vllm-ascend/pull/6477)
 - LoRA with tensor parallel and `--fully-sharded-loras` is now fixed and working. [#6650](https://github.com/vllm-project/vllm-ascend/pull/6650)
 - LMCacheAscendConnector is added as a new KV cache pooling solution for Ascend. [#6882](https://github.com/vllm-project/vllm-ascend/pull/6882)
-- W8A8C8 quantization is now supported for DeepSeek-V3.2 and GLM5 in PD-mix scenario. [#7029](https://github.com/vllm-project/vllm-ascend/pull/7029)
+- W8A8C8 quantization is now supported for DeepSeek-V3.2 in PD-mix scenario. [#7029](https://github.com/vllm-project/vllm-ascend/pull/7029)
 - [Experimental] Minimax-m2.5 model is now supported on Ascend NPU. [#7105](https://github.com/vllm-project/vllm-ascend/pull/7105)
 - [Experimental] Mooncake Layerwise Connector now supports hybrid attention manager with multiple KV cache groups. [#7022](https://github.com/vllm-project/vllm-ascend/pull/7022)
 - [Experimental] Prefix cache is now supported in hybrid model. [#7103](https://github.com/vllm-project/vllm-ascend/pull/7103)

tests/e2e/nightly/single_node/models/configs/GLM-5.yaml

@@ -0,0 +1,83 @@
+# ==========================================
+# Shared Configurations
+# ==========================================
+
+_envs: &envs
+  HCCL_BUFFSIZE: "200"
+  SERVER_PORT: "DEFAULT_PORT"
+  HCCL_OP_EXPANSION_MODE: "AIV"
+  OMP_PROC_BIND: "false"
+  OMP_NUM_THREADS: "1"
+  PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
+  VLLM_ASCEND_BALANCE_SCHEDULING: "1"
+
+_server_cmd: &server_cmd
+  - "--enable-expert-parallel"
+  - "--tensor-parallel-size"
+  - "16"
+  - "--data-parallel-size"
+  - "1"
+  - "--port"
+  - "$SERVER_PORT"
+  - "--max-model-len"
+  - "8192"
+  - "--max-num-batched-tokens"
+  - "4096"
+  - "--trust-remote-code"
+  - "--gpu-memory-utilization"
+  - "0.95"
+  - "--max-num-seqs"
+  - "8"
+  - "--quantization"
+  - "ascend"
+  - "--async-scheduling"
+  - "--additional-config"
+  - '{"enable_npugraph_ex": true,"fuse_muls_add":true,"multistream_overlap_shared_expert":true}'
+  - "--speculative-config"
+  - '{"num_speculative_tokens": 3, "method": "deepseek_mtp"}'
+
+_benchmarks: &benchmarks
+  acc:
+    case_type: accuracy
+    dataset_path: vllm-ascend/gsm8k-lite
+    request_conf: vllm_api_general_chat
+    dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_chat_prompt
+    max_out_len: 4096
+    batch_size: 8
+    baseline: 95
+    threshold: 5
+  perf:
+    case_type: performance
+    dataset_path: vllm-ascend/GSM8K-in3500-bs400
+    request_conf: vllm_api_stream_chat
+    dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_str_perf
+    num_prompts: 16
+    max_out_len: 1500
+    batch_size: 8
+    request_rate: 0
+    baseline: 1
+    threshold: 0.97
+
+# ==========================================
+# ACTUAL TEST CASES
+# ==========================================
+
+test_cases:
+  - name: "GLM-5-TP16-DP1-decodegraph"
+    model: "Eco-Tech/GLM-5-w4a8"
+    envs:
+      <<: *envs
+    server_cmd: *server_cmd
+    server_cmd_extra:
+      - "--compilation-config"
+      - '{"cudagraph_capture": [4,8,12,16,20,24,28,32], "cudagraph_model":"FULL_DECODE_ONLY"}'
+    benchmarks:
+      <<: *benchmarks
+
+  - name: "GLM-5-TP16-DP1-eager"
+    model: "Eco-Tech/GLM-5-w4a8"
+    envs:
+      <<: *envs
+    server_cmd: *server_cmd
+    benchmarks:
+      <<: *benchmarks