[Bug]: PD seperate (MoonCake) doesn't take effect because of IPV6 host ip

[mitseng]

Your current environment

The output of `python collect_env.py`

Collecting environment information...
PyTorch version: 2.7.1+cpu
Is debug build: False

OS: Debian GNU/Linux 12 (bookworm) (x86_64)
GCC version: (Debian 12.2.0-14+deb12u1) 12.2.0
Clang version: Could not collect
CMake version: version 3.25.1
Libc version: glibc-2.36

Python version: 3.11.9 (main, Dec 26 2024, 11:08:39) [GCC 12.2.0] (64-bit runtime)
Python platform: Linux-5.10.135.bsk.6-amd64-x86_64-with-glibc2.36

CPU:
Architecture:                    x86_64
CPU op-mode(s):                  32-bit, 64-bit
Address sizes:                   46 bits physical, 57 bits virtual
Byte Order:                      Little Endian
CPU(s):                          180
On-line CPU(s) list:             0-179
Vendor ID:                       GenuineIntel
Model name:                      Intel(R) Xeon(R) Platinum 8457C
CPU family:                      6
Model:                           143
Thread(s) per core:              2
Core(s) per socket:              45
Socket(s):                       2
Stepping:                        8
BogoMIPS:                        5199.53
Flags:                           fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx_vnni avx512_bf16 wbnoinvd arat avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid cldemote movdiri movdir64b fsrm md_clear serialize tsxldtrk arch_lbr amx_bf16 avx512_fp16 amx_tile amx_int8 arch_capabilities
Hypervisor vendor:               KVM
Virtualization type:             full
L1d cache:                       4.2 MiB (90 instances)
L1i cache:                       2.8 MiB (90 instances)
L2 cache:                        180 MiB (90 instances)
L3 cache:                        195 MiB (2 instances)
NUMA node(s):                    2
NUMA node0 CPU(s):               0-89
NUMA node1 CPU(s):               90-179
Vulnerability Itlb multihit:     Not affected
Vulnerability L1tf:              Not affected
Vulnerability Mds:               Not affected
Vulnerability Meltdown:          Not affected
Vulnerability Mmio stale data:   Not affected
Vulnerability Retbleed:          Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1:        Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:        Mitigation; Enhanced IBRS, IBPB conditional, RSB filling
Vulnerability Srbds:             Not affected
Vulnerability Tsx async abort:   Mitigation; TSX disabled

Versions of relevant libraries:
[pip3] numpy==1.26.4
[pip3] pyzmq==27.1.0
[pip3] torch==2.7.1+cpu
[pip3] torch_npu==2.7.1
[pip3] transformers==4.57.1
[conda] Could not collect
vLLM Version: 0.11.0
vLLM Ascend Version: 0.11.0rc1.dev198+gd913f9474.d20251110 (git sha: d913f9474, date: 20251110)

ENV Variables:
ATB_OPSRUNNER_KERNEL_CACHE_LOCAL_COUNT=1
ATB_STREAM_SYNC_EVERY_RUNNER_ENABLE=0
ATB_OPSRUNNER_SETUP_CACHE_ENABLE=1
ATB_WORKSPACE_MEM_ALLOC_GLOBAL=1
ATB_DEVICE_TILING_BUFFER_BLOCK_NUM=32
ASCEND_VISIBLE_DEVICES=1,2,12,3,10,5,14,15,4,13,8,7,0,6,9,11
ATB_STREAM_SYNC_EVERY_KERNEL_ENABLE=0
ASCEND_RUNTIME_OPTIONS=
ATB_OPSRUNNER_KERNEL_CACHE_GLOABL_COUNT=5
ATB_HOME_PATH=/usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_1
ASCEND_TOOLKIT_HOME=/usr/local/Ascend/ascend-toolkit/latest
ASCEND_PROCESS_LOG_PATH=/var/log/tiger/ascend_diag_logs/run_0/process_log
ATB_COMPARE_TILING_EVERY_KERNEL=0
ASCEND_OPP_PATH=/usr/local/Ascend/ascend-toolkit/latest/opp
LD_LIBRARY_PATH=/usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_1/lib:/usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_1/examples:/usr/local/Ascend/nnal/atb/latest/atb/cxx_abi_1/tests/atbopstest:/usr/local/Ascend/ascend-toolkit/latest/tools/aml/lib64:/usr/local/Ascend/ascend-toolkit/latest/tools/aml/lib64/plugin:/usr/local/Ascend/ascend-toolkit/latest/lib64:/usr/local/Ascend/ascend-toolkit/latest/lib64/plugin/opskernel:/usr/local/Ascend/ascend-toolkit/latest/lib64/plugin/nnengine:/usr/local/Ascend/ascend-toolkit/latest/opp/built-in/op_impl/ai_core/tbe/op_tiling/lib/linux/x86_64:/opt/tiger/native_libhdfs/lib/native:/opt/tiger/jdk/jdk8u265-b01/jre/lib/amd64/server:/opt/tiger/yarn_deploy/hadoop_current/lib/native:/opt/tiger/yarn_deploy/hadoop_current/lib/native/ufs:/opt/tiger/yarn_deploy/hadoop/lib/native:/opt/tiger/yarn_deploy/hadoop_current/lib/native:/opt/tiger/yarn_deploy/hadoop_current/lzo/lib:/usr/local/Ascend/ascend-toolkit/latest/lib64:/usr/local/Ascend/ascend-toolkit/latest/lib64/plugin/opskernel:/usr/local/Ascend/ascend-toolkit/latest/lib64/plugin/nnengine:/usr/local/Ascend/driver/lib64:/usr/local/Ascend/driver/lib64/common:/usr/local/Ascend/driver/lib64/driver::/usr/local/Ascend/driver/lib64:/usr/local/Ascend/driver/lib64/common:/usr/local/Ascend/driver/lib64/driver:/usr/local/Ascend/toolbox/latest/Ascend-DMI/lib64
ASCEND_AICPU_PATH=/usr/local/Ascend/ascend-toolkit/latest
ATB_STREAM_SYNC_EVERY_OPERATION_ENABLE=0
ASCEND_HOME_PATH=/usr/local/Ascend/ascend-toolkit/latest
ATB_MATMUL_SHUFFLE_K_ENABLE=1
ATB_WORKSPACE_MEM_ALLOC_ALG_TYPE=1
ATB_HOST_TILING_BUFFER_BLOCK_NUM=128
ATB_SHARE_MEMORY_NAME_SUFFIX=
TORCH_DEVICE_BACKEND_AUTOLOAD=1
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1


NPU:
+------------------------------------------------------------------------------------------------+
| npu-smi 24.1.rc2                 Version: 24.1.rc2                                             |
+---------------------------+---------------+----------------------------------------------------+
| NPU   Name                | Health        | Power(W)    Temp(C)           Hugepages-Usage(page)|
| Chip                      | Bus-Id        | AICore(%)   Memory-Usage(MB)  HBM-Usage(MB)        |
+===========================+===============+====================================================+
| 0     910B2C              | OK            | 90.4        44                0    / 0             |
| 0                         | 0000:75:01.0  | 0           0    / 0          3446 / 65536         |
+===========================+===============+====================================================+
| 1     910B2C              | OK            | 93.1        45                0    / 0             |
| 0                         | 0000:6F:01.0  | 0           0    / 0          3426 / 65536         |
+===========================+===============+====================================================+
| 2     910B2C              | OK            | 89.1        42                0    / 0             |
| 0                         | 0000:71:01.0  | 0           0    / 0          3425 / 65536         |
+===========================+===============+====================================================+
| 3     910B2C              | OK            | 93.3        45                0    / 0             |
| 0                         | 0000:6B:01.0  | 0           0    / 0          3425 / 65536         |
+===========================+===============+====================================================+
| 4     910B2C              | OK            | 99.3        44                0    / 0             |
| 0                         | 0000:69:01.0  | 0           0    / 0          3426 / 65536         |
+===========================+===============+====================================================+
| 5     910B2C              | OK            | 94.8        46                0    / 0             |
| 0                         | 0000:67:01.0  | 0           0    / 0          3425 / 65536         |
+===========================+===============+====================================================+
| 6     910B2C              | OK            | 99.7        46                0    / 0             |
| 0                         | 0000:65:01.0  | 0           0    / 0          3426 / 65536         |
+===========================+===============+====================================================+
| 7     910B2C              | OK            | 92.3        45                0    / 0             |
| 0                         | 0000:73:01.0  | 0           0    / 0          3425 / 65536         |
+===========================+===============+====================================================+
| 8     910B2C              | OK            | 93.4        45                0    / 0             |
| 0                         | 0000:75:02.0  | 0           0    / 0          3437 / 65536         |
+===========================+===============+====================================================+
| 9     910B2C              | OK            | 94.5        45                0    / 0             |
| 0                         | 0000:6F:02.0  | 0           0    / 0          3424 / 65536         |
+===========================+===============+====================================================+
| 10    910B2C              | OK            | 94.4        43                0    / 0             |
| 0                         | 0000:71:02.0  | 0           0    / 0          3425 / 65536         |
+===========================+===============+====================================================+
| 11    910B2C              | OK            | 94.5        46                0    / 0             |
| 0                         | 0000:6B:02.0  | 0           0    / 0          3420 / 65536         |
+===========================+===============+====================================================+
| 12    910B2C              | OK            | 93.2        45                0    / 0             |
| 0                         | 0000:69:02.0  | 0           0    / 0          3424 / 65536         |
+===========================+===============+====================================================+
| 13    910B2C              | OK            | 97.7        45                0    / 0             |
| 0                         | 0000:67:02.0  | 0           0    / 0          3424 / 65536         |
+===========================+===============+====================================================+
| 14    910B2C              | OK            | 91.4        43                0    / 0             |
| 0                         | 0000:65:02.0  | 0           0    / 0          3425 / 65536         |
+===========================+===============+====================================================+
| 15    910B2C              | OK            | 97.6        45                0    / 0             |
| 0                         | 0000:73:02.0  | 0           0    / 0          3423 / 65536         |
+===========================+===============+====================================================+
+---------------------------+---------------+----------------------------------------------------+
| NPU     Chip              | Process id    | Process name             | Process memory(MB)      |
+===========================+===============+====================================================+
| No running processes found in NPU 0                                                            |
+===========================+===============+====================================================+
| No running processes found in NPU 1                                                            |
+===========================+===============+====================================================+
| No running processes found in NPU 2                                                            |
+===========================+===============+====================================================+
| No running processes found in NPU 3                                                            |
+===========================+===============+====================================================+
| No running processes found in NPU 4                                                            |
+===========================+===============+====================================================+
| No running processes found in NPU 5                                                            |
+===========================+===============+====================================================+
| No running processes found in NPU 6                                                            |
+===========================+===============+====================================================+
| No running processes found in NPU 7                                                            |
+===========================+===============+====================================================+
| No running processes found in NPU 8                                                            |
+===========================+===============+====================================================+
| No running processes found in NPU 9                                                            |
+===========================+===============+====================================================+
| No running processes found in NPU 10                                                           |
+===========================+===============+====================================================+
| No running processes found in NPU 11                                                           |
+===========================+===============+====================================================+
| No running processes found in NPU 12                                                           |
+===========================+===============+====================================================+
| No running processes found in NPU 13                                                           |
+===========================+===============+====================================================+
| No running processes found in NPU 14                                                           |
+===========================+===============+====================================================+
| No running processes found in NPU 15                                                           |
+===========================+===============+====================================================+

CANN:
package_name=Ascend-cann-toolkit
version=8.3.RC1
innerversion=V100R001C23SPC001B235
compatible_version=[V100R001C15],[V100R001C18],[V100R001C19],[V100R001C20],[V100R001C21],[V100R001C23]
arch=x86_64
os=linux
path=/usr/local/Ascend/ascend-toolkit/8.3.RC1/x86_64-linux

🐛 Describe the bug

ERROR Message from Decode:

(Worker_TP1 pid=113078) ERROR 11-10 20:25:57 [mooncake_connector.py:329] Failed to transfer KV cache for request cmpl-b51d45c6-33bf-4b76-98c5-fcbcc2f72334-0: Mooncake transfer failed, ret: -1
(Worker_TP4 pid=113591) ERROR 11-10 20:25:57 [mooncake_connector.py:410] Mooncake transfer failed for request cmpl-b51d45c6-33bf-4b76-98c5-fcbcc2f72334-0
(Worker_TP4 pid=113591) ERROR 11-10 20:25:57 [mooncake_connector.py:329] Failed to transfer KV cache for request cmpl-b51d45c6-33bf-4b76-98c5-fcbcc2f72334-0: Mooncake transfer failed, ret: -1
E20251110 20:25:57.753341 124570 transfer_metadata_plugin.cpp:969] SocketHandShakePlugin: failed to get IP address of peer server 2605:340:cd51:4900:3b92:43bb:ec8:c354:16051, check DNS and /etc/hosts, or use IPv4 address instead: Resource temporarily unavailable [11]
E20251110 20:25:57.753441 124565 transfer_metadata_plugin.cpp:969] SocketHandShakePlugin: failed to get IP address of peer server 2605:340:cd51:4900:3b92:43bb:ec8:c354:15393, check DNS and /etc/hosts, or use IPv4 address instead: Resource temporarily unavailable [11]
(Worker_TP0 pid=112945) ERROR 11-10 20:25:57 [mooncake_connector.py:410] Mooncake transfer failed for request cmpl-5de53eb9-c853-451a-91c5-a4f0e822e5ca-0
E20251110 20:25:57.753445 124569 transfer_metadata_plugin.cpp:969] SocketHandShakePlugin: failed to get IP address of peer server 2605:340:cd51:4900:3b92:43bb:ec8:c354:16791, check DNS and /etc/hosts, or use IPv4 address instead: Resource temporarily unavailable [11]
E20251110 20:25:57.753521 124563 transfer_metadata_plugin.cpp:969] SocketHandShakePlugin: failed to get IP address of peer server 2605:340:cd51:4900:3b92:43bb:ec8:c354:15961, check DNS and /etc/hosts, or use IPv4 address instead: Resource temporarily unavailable [11]
(Worker_TP3 pid=113415) ERROR 11-10 20:25:57 [mooncake_connector.py:410] Mooncake transfer failed for request cmpl-5de53eb9-c853-451a-91c5-a4f0e822e5ca-0
E20251110 20:25:57.753563 124564 transfer_metadata_plugin.cpp:969] SocketHandShakePlugin: failed to get IP address of peer server 2605:340:cd51:4900:3b92:43bb:ec8:c354:16038, check DNS and /etc/hosts, or use IPv4 address instead: Resource temporarily unavailable [11]
E20251110 20:25:57.753571 124566 transfer_metadata_plugin.cpp:969] SocketHandShakePlugin: failed to get IP address of peer server 2605:340:cd51:4900:3b92:43bb:ec8:c354:15920, check DNS and /etc/hosts, or use IPv4 address instead: Resource temporarily unavailable [11]
(Worker_TP0 pid=112945) ERROR 11-10 20:25:57 [mooncake_connector.py:329] Failed to transfer KV cache for request cmpl-5de53eb9-c853-451a-91c5-a4f0e822e5ca-0: Mooncake transfer failed, ret: -1
(Worker_TP3 pid=113415) ERROR 11-10 20:25:57 [mooncake_connector.py:329] Failed to transfer KV cache for request cmpl-5de53eb9-c853-451a-91c5-a4f0e822e5ca-0: Mooncake transfer failed, ret: -1
(Worker_TP2 pid=113223) ERROR 11-10 20:25:57 [mooncake_connector.py:410] Mooncake transfer failed for request cmpl-5de53eb9-c853-451a-91c5-a4f0e822e5ca-0
(Worker_TP6 pid=113982) ERROR 11-10 20:25:57 [mooncake_connector.py:410] Mooncake transfer failed for request cmpl-5de53eb9-c853-451a-91c5-a4f0e822e5ca-0
(Worker_TP6 pid=113982) ERROR 11-10 20:25:57 [mooncake_connector.py:329] Failed to transfer KV cache for request cmpl-5de53eb9-c853-451a-91c5-a4f0e822e5ca-0: Mooncake transfer failed, ret: -1
(Worker_TP7 pid=114181) ERROR 11-10 20:25:57 [mooncake_connector.py:410] Mooncake transfer failed for request cmpl-5de53eb9-c853-451a-91c5-a4f0e822e5ca-0
(Worker_TP2 pid=113223) ERROR 11-10 20:25:57 [mooncake_connector.py:329] Failed to transfer KV cache for request cmpl-5de53eb9-c853-451a-91c5-a4f0e822e5ca-0: Mooncake transfer failed, ret: -1
(Worker_TP5 pid=113752) ERROR 11-10 20:25:57 [mooncake_connector.py:410] Mooncake transfer failed for request cmpl-5de53eb9-c853-451a-91c5-a4f0e822e5ca-0
(Worker_TP7 pid=114181) ERROR 11-10 20:25:57 [mooncake_connector.py:329] Failed to transfer KV cache for request cmpl-5de53eb9-c853-451a-91c5-a4f0e822e5ca-0: Mooncake transfer failed, ret: -1
(Worker_TP5 pid=113752) ERROR 11-10 20:25:57 [mooncake_connector.py:329] Failed to transfer KV cache for request cmpl-5de53eb9-c853-451a-91c5-a4f0e822e5ca-0: Mooncake transfer failed, ret: -1
E20251110 20:25:57.753978 124567 transfer_metadata_plugin.cpp:969] SocketHandShakePlugin: failed to get IP address of peer server 2605:340:cd51:4900:3b92:43bb:ec8:c354:15758, check DNS and /etc/hosts, or use IPv4 address instead: Resource temporarily unavailable [11]
(Worker_TP1 pid=113078) ERROR 11-10 20:25:57 [mooncake_connector.py:410] Mooncake transfer failed for request cmpl-5de53eb9-c853-451a-91c5-a4f0e822e5ca-0
E20251110 20:25:57.754192 124568 transfer_metadata_plugin.cpp:969] SocketHandShakePlugin: failed to get IP address of peer server 2605:340:cd51:4900:3b92:43bb:ec8:c354:16119, check DNS and /etc/hosts, or use IPv4 address instead: Resource temporarily unavailable [11]
(Worker_TP1 pid=113078) ERROR 11-10 20:25:57 [mooncake_connector.py:329] Failed to transfer KV cache for request cmpl-5de53eb9-c853-451a-91c5-a4f0e822e5ca-0: Mooncake transfer failed, ret: -1
(Worker_TP4 pid=113591) ERROR 11-10 20:25:57 [mooncake_connector.py:410] Mooncake transfer failed for request cmpl-5de53eb9-c853-451a-91c5-a4f0e822e5ca-0
(Worker_TP4 pid=113591) ERROR 11-10 20:25:57 [mooncake_connector.py:329] Failed to transfer KV cache for request cmpl-5de53eb9-c853-451a-91c5-a4f0e822e5ca-0: Mooncake transfer failed, ret: -1
(APIServer pid=112643) INFO 11-10 20:26:04 [loggers.py:127] Engine 000: Avg prompt throughput: 2100.0 tokens/s, Avg generation throughput: 146.8 tokens/s, Running: 8 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.4%, Prefix cache hit rate: 0.0%

[LCAIZJ]

Could you please share the startup script and the plog error logs?

[mitseng]

Could you please share the startup script and the plog error logs?

My startup script：

# prefill
unset ftp_proxy
unset https_proxy
unset http_proxy
export HCCL_IF_IP=2605:340:cd51:4900:3b92:43bb:ec8:c354  # I tried both
export HCCL_IF_IP=127.0.0.1  # I tried both
export GLOO_SOCKET_IFNAME="eth0"  # network card name
export TP_SOCKET_IFNAME="eth0"
export HCCL_SOCKET_IFNAME="eth0"
export HCCL_IF_BASE_PORT=58888
export VLLM_USE_V1=1
# export HCCL_BUFFSIZE=1024
export ASCEND_RT_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
export OMP_PROC_BIND=false
export OMP_NUM_THREADS=10
export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/python/site-packages:/mnt/bn/nas-assinfra-hl-03/work/Mooncake/build/mooncake-transfer-engine/src/:/mnt/bn/nas-assinfra-hl-03/work/vllm-ascend/vllm_ascend/lib/:$LD_LIBRARY_PATH
# export PYTORCH_NPU_ALLOC_CONF=max_split_size_mb:256

python -m vllm.entrypoints.openai.api_server \
  --model /mnt/bn/nas-assinfra-hl-03/ckpt/Qwen3-235B-A22B-Instruct-2507-w8a8-QuaRot \
  --host 0.0.0.0 \
  --port 8004 \
  --api-server-count 1 \
  --tensor-parallel-size 8 \
  --no-enable-expert-parallel \
  --seed 1024 \
  --enforce-eager \
  --distributed-executor-backend mp \
  --served-model-name qwen235b \
  --max-model-len 8192 \
  --max-num-batched-tokens 4096 \
  --max-num_seqs 22 \
  --quantization ascend \
  --trust-remote-code \
  --gpu-memory-utilization 0.9 \
  --kv-transfer-config \
  '{"kv_connector": "MooncakeConnector",
  "kv_role": "kv_producer",
  "kv_port": "37777",
  "engine_id": "0",
  "kv_connector_module_path": "vllm_ascend.distributed.mooncake_connector",
  "kv_connector_extra_config": {
            "prefill": {
                    "dp_size": 1,
                    "tp_size": 8
             },
             "decode": {
                    "dp_size": 1,
                    "tp_size": 8
             }
      }
  }'

# decode
unset ftp_proxy
unset https_proxy
unset http_proxy
export HCCL_IF_IP=2605:340:cd51:4900:3b92:43bb:ec8:c354
export HCCL_IF_IP=127.0.0.1
export GLOO_SOCKET_IFNAME="eth0"  # network card name
export TP_SOCKET_IFNAME="eth0"
export HCCL_SOCKET_IFNAME="eth0"
export HCCL_IF_BASE_PORT=60016
export VLLM_USE_V1=1
# export HCCL_BUFFSIZE=2048
export ASCEND_RT_VISIBLE_DEVICES=8,9,10,11,12,13,14,15
export OMP_PROC_BIND=false
export OMP_NUM_THREADS=10
export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/python/site-packages:/mnt/bn/nas-assinfra-hl-03/work/Mooncake/build/mooncake-transfer-engine/src/:/mnt/bn/nas-assinfra-hl-03/work/vllm-ascend/vllm_ascend/lib/:$LD_LIBRARY_PATH
# export PYTORCH_NPU_ALLOC_CONF=max_split_size_mb:256

python -m vllm.entrypoints.openai.api_server \
  --model /mnt/bn/nas-assinfra-hl-03/ckpt/Qwen3-235B-A22B-Instruct-2507-w8a8-QuaRot \
  --host 0.0.0.0 \
  --port 8008 \
  --api-server-count 1 \
  --tensor-parallel-size 8 \
  --no-enable-expert-parallel \
  --seed 1024 \
  --distributed-executor-backend mp \
  --served-model-name qwen235b \
  --max-model-len 8192 \
  --max-num-batched-tokens 4096 \
  --max-num_seqs 22 \
  --quantization ascend \
  --trust-remote-code \
  --no-enable-prefix-caching \
  --gpu-memory-utilization 0.9 \
  --compilation-config '{"cudagraph_capture_sizes":[1,6,8,18,20,22]}' \
  --kv-transfer-config \
  '{"kv_connector": "MooncakeConnector",
  "kv_role": "kv_consumer",
  "kv_port": "38888",
  "engine_id": "1",
  "kv_connector_module_path": "vllm_ascend.distributed.mooncake_connector",
  "kv_connector_extra_config": {
            "prefill": {
                    "dp_size": 1,
                    "tp_size": 8
             },
             "decode": {
                    "dp_size": 1,
                    "tp_size": 8
             }
      }
  }'

# proxy
python /mnt/bn/nas-assinfra-hl-03/work/vllm-ascend/examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py \
    --port 8080 \
    --prefiller-port 8004 \
    --decoder-ports 8008

p-d instances are on same node.

[LCAIZJ]

Try changing

"kv_connector_extra_config": {
            "prefill": {
                    "dp_size": 1,
                    "tp_size": 8
             },
             "decode": {
                    "dp_size": 1,
                    "tp_size": 8
             }
      }

to

"kv_connector_extra_config": {
            "use_ascend_direct": true,
            "prefill": {
                    "dp_size": 1,
                    "tp_size": 8
             },
             "decode": {
                    "dp_size": 1,
                    "tp_size": 8
             }
      }

Also, could you check what error plog is reporting? grep -rn ERROR /root/ascend/log

[mitseng]

Try changing

"kv_connector_extra_config": {
"prefill": {
"dp_size": 1,
"tp_size": 8
},
"decode": {
"dp_size": 1,
"tp_size": 8
}
}
to

"kv_connector_extra_config": {
"use_ascend_direct": true,
"prefill": {
"dp_size": 1,
"tp_size": 8
},
"decode": {
"dp_size": 1,
"tp_size": 8
}
}
Also, could you check what error plog is reporting? grep -rn ERROR /root/ascend/log

after adding "use_ascend_direct": true,, Prefill failed when init model, error log:

(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]     maybe_offload_to_cpu(layer_fn(prefix=f"{prefix}.{idx}"))
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]   File "/mnt/bn/nas-assinfra-hl-03/work/vllm/vllm/model_executor/models/qwen3_moe.py", line 391, in <lambda>
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]     lambda prefix: Qwen3MoeDecoderLayer(vllm_config=vllm_config,
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]   File "/mnt/bn/nas-assinfra-hl-03/work/vllm/vllm/model_executor/models/qwen3_moe.py", line 331, in __init__
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]     self.mlp = Qwen3MoeSparseMoeBlock(vllm_config=vllm_config,
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]   File "/mnt/bn/nas-assinfra-hl-03/work/vllm/vllm/model_executor/models/qwen3_moe.py", line 144, in __init__
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]     self.experts = FusedMoE(num_experts=self.n_routed_experts,
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]   File "/mnt/bn/nas-assinfra-hl-03/work/vllm-ascend/vllm_ascend/ops/common_fused_moe.py", line 155, in __init__
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]     super().__init__(*args, **kwargs)
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]   File "/mnt/bn/nas-assinfra-hl-03/work/vllm/vllm/model_executor/layers/fused_moe/layer.py", line 1104, in __init__
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]     else quant_config.get_quant_method(self, prefix))
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]   File "/mnt/bn/nas-assinfra-hl-03/work/vllm-ascend/vllm_ascend/quantization/quant_config.py", line 126, in get_quant_method
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]     return AscendFusedMoEMethod(self, prefix,
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]   File "/mnt/bn/nas-assinfra-hl-03/work/vllm-ascend/vllm_ascend/quantization/quant_config.py", line 389, in __init__
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]     self.quant_method = get_quant_method(quant_config.quant_description,
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]   File "/mnt/bn/nas-assinfra-hl-03/work/vllm-ascend/vllm_ascend/quantization/utils.py", line 81, in get_quant_method
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]     return method_cls()
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]            ^^^^^^^^^^^^
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]   File "/mnt/bn/nas-assinfra-hl-03/work/vllm-ascend/vllm_ascend/quantization/w8a8_dynamic.py", line 137, in __init__
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]     self.moe_all_to_all_group_name = backend.get_hccl_comm_name(
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]                                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597] RuntimeError: create_config:torch_npu/csrc/distributed/HCCLUtils.cpp:149 HCCL function error: hcclCommInitRootInfoConfig(numRanks, &rootInfo, rank, config, &(comm->hcclComm_)), error code is 7
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597] [ERROR] 2025-11-11-16:24:15 (PID:178598, Device:0, RankID:-1) ERR02200 DIST call hccl api failed.
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597] [PID: 178598] 2025-11-11-16:24:15.150.623 HCCP_Process_Initialization_Failure(EJ0001): Failed to initialize the HCCP process. Reason: Maybe the last training process is running.
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]         Solution: Wait for 10s after killing the last training process and try again.
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]         TraceBack (most recent call last):
(Worker_TP0 pid=178598) ERROR 11-11 16:24:15 [multiproc_executor.py:597]         tsd client wait response fail, hostpid:2209492, device response code[1]. unknown device error.[FUNC:WaitRsp][FILE:process_mode_manager.cpp][LINE:270]

plog is empty

hdk Version: 24.1.rc2, can't upgrade in short time.

[LCAIZJ]

char service[16];
sprintf(service, "%u", rpc_port);
if (getaddrinfo(ip_or_host_name.c_str(), service, &hints, &result)) {
    PLOG(ERROR)
        << "SocketHandShakePlugin: failed to get IP address of peer "
           "server "
        << ip_or_host_name << ":" << rpc_port
        << ", check DNS and /etc/hosts, or use IPv4 address instead";
    return ERR_DNS;
}

It looks like an error was returned after calling getaddrinfo.

[LCAIZJ]

Try adding an environment variable: export MC_USE_IPV6=1.

[mitseng]

Try adding an environment variable: export MC_USE_IPV6=1.

doesn't seam to work, log from D Node：

E20251112 17:02:55.861495 33154 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d109368000, length: 884736, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861500 33158 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d100840000, length: 32768, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861505 33154 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d109440000, length: 32768, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861510 33158 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d109368000, length: 884736, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861518 33154 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d111f68000, length: 884736, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861521 33158 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d109440000, length: 32768, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861528 33154 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d112040000, length: 32768, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861531 33158 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d111f68000, length: 884736, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
(Worker_TP5 pid=19032) ERROR 11-12 17:02:55 [mooncake_connector.py:410] Mooncake transfer failed for request cmpl-c9dbd789-6854-43c9-a67c-37d3db01a9fb-0
E20251112 17:02:55.861541 33154 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d11ab68000, length: 884736, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861543 33158 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d112040000, length: 32768, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861553 33154 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d11ac40000, length: 32768, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861555 33158 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d11ab68000, length: 884736, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861567 33154 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d123768000, length: 884736, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861567 33158 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d11ac40000, length: 32768, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861581 33154 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d123840000, length: 32768, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861584 33158 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d123768000, length: 884736, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
(Worker_TP5 pid=19032) ERROR 11-12 17:02:55 [mooncake_connector.py:329] Failed to transfer KV cache for request cmpl-c9dbd789-6854-43c9-a67c-37d3db01a9fb-0: Mooncake transfer failed, ret: -1
E20251112 17:02:55.861596 33158 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d123840000, length: 32768, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
(Worker_TP1 pid=18318) ERROR 11-12 17:02:55 [mooncake_connector.py:410] Mooncake transfer failed for request cmpl-c9dbd789-6854-43c9-a67c-37d3db01a9fb-0
(Worker_TP3 pid=18637) ERROR 11-12 17:02:55 [mooncake_connector.py:410] Mooncake transfer failed for request cmpl-c9dbd789-6854-43c9-a67c-37d3db01a9fb-0
(Worker_TP1 pid=18318) ERROR 11-12 17:02:55 [mooncake_connector.py:329] Failed to transfer KV cache for request cmpl-c9dbd789-6854-43c9-a67c-37d3db01a9fb-0: Mooncake transfer failed, ret: -1
(Worker_TP3 pid=18637) ERROR 11-12 17:02:55 [mooncake_connector.py:329] Failed to transfer KV cache for request cmpl-c9dbd789-6854-43c9-a67c-37d3db01a9fb-0: Mooncake transfer failed, ret: -1
(APIServer pid=17818) INFO 11-12 17:02:59 [loggers.py:127] Engine 000: Avg prompt throughput: 2800.0 tokens/s, Avg generation throughput: 80.6 tokens/s, Running: 8 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.2%, Prefix cache hit rate: 0.0%

[LCAIZJ]

Try adding an environment variable: export MC_USE_IPV6=1.

doesn't seam to work, log from D Node：

E20251112 17:02:55.861495 33154 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d109368000, length: 884736, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861500 33158 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d100840000, length: 32768, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861505 33154 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d109440000, length: 32768, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861510 33158 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d109368000, length: 884736, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861518 33154 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d111f68000, length: 884736, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861521 33158 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d109440000, length: 32768, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861528 33154 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d112040000, length: 32768, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861531 33158 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d111f68000, length: 884736, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
(Worker_TP5 pid=19032) ERROR 11-12 17:02:55 [mooncake_connector.py:410] Mooncake transfer failed for request cmpl-c9dbd789-6854-43c9-a67c-37d3db01a9fb-0
E20251112 17:02:55.861541 33154 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d11ab68000, length: 884736, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861543 33158 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d112040000, length: 32768, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861553 33154 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d11ac40000, length: 32768, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861555 33158 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d11ab68000, length: 884736, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861567 33154 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d123768000, length: 884736, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861567 33158 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d11ac40000, length: 32768, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861581 33154 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d123840000, length: 32768, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
E20251112 17:02:55.861584 33158 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d123768000, length: 884736, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
(Worker_TP5 pid=19032) ERROR 11-12 17:02:55 [mooncake_connector.py:329] Failed to transfer KV cache for request cmpl-c9dbd789-6854-43c9-a67c-37d3db01a9fb-0: Mooncake transfer failed, ret: -1
E20251112 17:02:55.861596 33158 tcp_transport.cpp:480] TcpTransport::startTransfer encountered an ASIO exception. Slice details - source_addr: 0x12d123840000, length: 32768, opcode: 0, target_id: 1. Exception: resolve: Host not found (authoritative)
(Worker_TP1 pid=18318) ERROR 11-12 17:02:55 [mooncake_connector.py:410] Mooncake transfer failed for request cmpl-c9dbd789-6854-43c9-a67c-37d3db01a9fb-0
(Worker_TP3 pid=18637) ERROR 11-12 17:02:55 [mooncake_connector.py:410] Mooncake transfer failed for request cmpl-c9dbd789-6854-43c9-a67c-37d3db01a9fb-0
(Worker_TP1 pid=18318) ERROR 11-12 17:02:55 [mooncake_connector.py:329] Failed to transfer KV cache for request cmpl-c9dbd789-6854-43c9-a67c-37d3db01a9fb-0: Mooncake transfer failed, ret: -1
(Worker_TP3 pid=18637) ERROR 11-12 17:02:55 [mooncake_connector.py:329] Failed to transfer KV cache for request cmpl-c9dbd789-6854-43c9-a67c-37d3db01a9fb-0: Mooncake transfer failed, ret: -1
(APIServer pid=17818) INFO 11-12 17:02:59 [loggers.py:127] Engine 000: Avg prompt throughput: 2800.0 tokens/s, Avg generation throughput: 80.6 tokens/s, Running: 8 reqs, Waiting: 0 reqs, GPU KV cache usage: 5.2%, Prefix cache hit rate: 0.0%

This is a new issue, indicating that the previous error has been resolved.

[LCAIZJ]

Why are you using TCP Transport? I noticed that the TCP Transport doesn't support IPv6 during hostname resolution—it might be necessary to submit a PR to the Mooncake community.

[mitseng]

Why are you using TCP Transport? I noticed that the TCP Transport doesn't support IPv6 during hostname resolution—it might be necessary to submit a PR to the Mooncake community.

TCP Transport dosen't seem to be neccesary, can I configure other transport?

I'm using mooncake v0.3.7.post2

[LCAIZJ]

Why are you using TCP Transport? I noticed that the TCP Transport doesn't support IPv6 during hostname resolution—it might be necessary to submit a PR to the Mooncake community.

TCP Transport dosen't seem to be neccesary, can I configure other transport?

I'm using mooncake v0.3.7.post2

When building Mooncake, use the parameter -DUSE_ASCEND_DIRECT=ON to enable the ADXL transport.

[mitseng]

Why are you using TCP Transport? I noticed that the TCP Transport doesn't support IPv6 during hostname resolution—it might be necessary to submit a PR to the Mooncake community.

TCP Transport dosen't seem to be neccesary, can I configure other transport?
I'm using mooncake v0.3.7.post2

When building Mooncake, use the parameter -DUSE_ASCEND_DIRECT=ON to enable the ADXL transport.

I did, my build config:

cd Mooncake
git checkout v0.3.7.post2
sudo bash dependencies.sh -y
mkdir build
cd build
cmake .. -USE_ASCEND_DIRECT=ON
make -j
sudo make install

[liziyu179]

cmake .. -DUSE_ASCEND_DIRECT=ON

Why are you using TCP Transport? I noticed that the TCP Transport doesn't support IPv6 during hostname resolution—it might be necessary to submit a PR to the Mooncake community.

TCP Transport dosen't seem to be neccesary, can I configure other transport?
I'm using mooncake v0.3.7.post2

When building Mooncake, use the parameter -DUSE_ASCEND_DIRECT=ON to enable the ADXL transport.

I did, my build config:

cd Mooncake
git checkout v0.3.7.post2
sudo bash dependencies.sh -y
mkdir build
cd build
cmake .. -USE_ASCEND_DIRECT=ON
make -j
sudo make install

it should be cmake .. -DUSE_ASCEND_DIRECT=ON

[liziyu179]

Currently, the Ascend Direct Xfer Library backend for Mooncake does not support IPV6 and will be supported as soon as possible.