MetaX-Tech Developer Forum 论坛首页
  • 沐曦开发者
search
Sign in

GZZ

  • Members
  • Joined 2026年8月14日
  • message 帖子
  • forum 主题
  • favorite 关注者
  • favorite_border Follows
  • person_outline 详细信息

GZZ has posted 6 messages.

  • See post chevron_right
    GZZ
    Members
    DeepSeek-V4-Flash-0731-W8A8部署 解决中 2026年10月8日 10:58

    请问一下,有适配计划吗

  • See post chevron_right
    GZZ
    Members
    DeepSeek-V4-Flash-0731-W8A8部署 解决中 2026年9月30日 10:01

    当前发布的metax-vllm:0.27.0可以适配 DeepSeek-V4-Flash-0731-W8A8吗

  • See post chevron_right
    GZZ
    Members
    vllm-metax:0.25版本支持deepseek-v4-flash-0731部署了吗 已解决 2026年9月9日 11:19

    如题vllm-metax:0.25版本支持deepseek-v4-flash-0731部署了吗

  • See post chevron_right
    GZZ
    Members
    显卡C500 64G 单卡部署 metax-tech/Qwen3-30B-A3B-W8A8 输出异常 已解决 2026年8月31日 16:09

    收到 感谢

  • See post chevron_right
    GZZ
    Members
    显卡C500 64G 单卡部署 metax-tech/Qwen3-30B-A3B-W8A8 输出异常 已解决 2026年8月31日 14:33

    1.服务器厂家:New H3C Technologies CO., Ltd
    2.GPU型号:Metax C500X
    3.MX-SMI: 2.3.1
    Kernel Mode Driver Version : 3.8.30
    MACA Version: 3.7.2.0
    BIOS VERSION: 1.25.2.0
    4.操作系统内核:4.19.90-17.5.ky10.arrch64
    5.是否开启CPU虚拟化:未开启

    6.mx-smi回显:
    [root@k8s-gpu55 ~]# mx-smi
    mx-smi version: 2.3.1

    =================== MetaX System Management Interface Log ===================
    Timestamp : Mon Aug 31 11:21:40 2026

    Attached GPUs : 8
    +---------------------------------------------------------------------------------+
    | MX-SMI 2.3.1 Kernel Mode Driver Version: 3.8.30 |
    | MACA Version: 3.7.2.0 BIOS Version: 1.25.2.0 |
    |------------------+-----------------+---------------------+----------------------|
    | Board Name | GPU Persist-M | Bus-id | GPU-Util sGPU-M |
    | Pwr:Usage/Cap | Temp Perf | Memory-Usage | GPU-State |
    |==================+=================+=====================+======================|
    | 0 MetaX C500X | 0 N/A | 0000:08:00.0 | 0% Disabled |
    | 63W / 350W | 37C N/A | 874/65536 MiB | Available |
    +------------------+-----------------+---------------------+----------------------+
    | 1 MetaX C500X | 1 N/A | 0000:09:00.0 | 0% Disabled |
    | 63W / 350W | 37C N/A | 874/65536 MiB | Available |
    +------------------+-----------------+---------------------+----------------------+
    | 2 MetaX C500X | 2 N/A | 0000:0e:00.0 | 0% Disabled |
    | 77W / 350W | 37C N/A | 61207/65536 MiB | Available |
    +------------------+-----------------+---------------------+----------------------+
    | 3 MetaX C500X | 3 N/A | 0000:11:00.0 | 0% Disabled |
    | 64W / 350W | 36C N/A | 874/65536 MiB | Available |
    +------------------+-----------------+---------------------+----------------------+
    | 4 MetaX C500X | 4 N/A | 0000:32:00.0 | 0% Disabled |
    | 63W / 350W | 35C N/A | 874/65536 MiB | Available |
    +------------------+-----------------+---------------------+----------------------+
    | 5 MetaX C500X | 5 N/A | 0000:38:00.0 | 0% Disabled |
    | 61W / 350W | 35C N/A | 874/65536 MiB | Available |
    +------------------+-----------------+---------------------+----------------------+
    | 6 MetaX C500X | 6 N/A | 0000:3b:00.0 | 0% Disabled |
    | 62W / 350W | 37C N/A | 874/65536 MiB | Available |
    +------------------+-----------------+---------------------+----------------------+
    | 7 MetaX C500X | 7 N/A | 0000:3c:00.0 | 0% Disabled |
    | 67W / 350W | 38C N/A | 874/65536 MiB | Available |
    +------------------+-----------------+---------------------+----------------------+

    +---------------------------------------------------------------------------------+
    | Process: |
    | GPU PID Process Name GPU Memory |
    | Usage(MiB) |
    |=================================================================================|
    | 2 2253049 VLLM::EngineCor 60332 |
    +---------------------------------------------------------------------------------+

    7.容器info

    [root@k8s-gpu55 ~]# crictl info
    {
    "status": {
    "conditions": [
    {
    "type": "RuntimeReady",
    "status": true,
    "reason": "",
    "message": ""
    },
    {
    "type": "NetworkReady",
    "status": true,
    "reason": "",
    "message": ""
    }
    ]
    },
    "cniconfig": {
    "PluginDirs": [
    "/opt/cni/bin"
    ],
    "PluginConfDir": "/etc/cni/net.d",
    "PluginMaxConfNum": 1,
    "Prefix": "eth",
    "Networks": [
    {
    "Config": {
    "Name": "cni-loopback",
    "CNIVersion": "0.3.1",
    "Plugins": [
    {
    "Network": {
    "type": "loopback",
    "ipam": {},
    "dns": {}
    },
    "Source": "{\"type\":\"loopback\"}"
    }
    ],
    "Source": "{\n\"cniVersion\": \"0.3.1\",\n\"name\": \"cni-loopback\",\n\"plugins\": [{\n \"type\": \"loopback\"\n}]\n}"
    },
    "IFName": "lo"
    },
    {
    "Config": {
    "Name": "cbr0",
    "CNIVersion": "0.3.1",
    "Plugins": [
    {
    "Network": {
    "type": "flannel",
    "ipam": {},
    "dns": {}
    },
    "Source": "{\"delegate\":{\"hairpinMode\":true,\"isDefaultGateway\":true},\"type\":\"flannel\"}"
    },
    {
    "Network": {
    "type": "portmap",
    "capabilities": {
    "portMappings": true
    },
    "ipam": {},
    "dns": {}
    },
    "Source": "{\"capabilities\":{\"portMappings\":true},\"type\":\"portmap\"}"
    }
    ],
    "Source": "{\n \"name\": \"cbr0\",\n \"cniVersion\": \"0.3.1\",\n \"plugins\": [\n {\n \"type\": \"flannel\",\n \"delegate\": {\n \"hairpinMode\": true,\n \"isDefaultGateway\": true\n }\n },\n {\n \"type\": \"portmap\",\n \"capabilities\": {\n \"portMappings\": true\n }\n }\n ]\n}\n"
    },
    "IFName": "eth0"
    }
    ]
    },
    "config": {
    "containerd": {
    "snapshotter": "overlayfs",
    "defaultRuntimeName": "nvidia",
    "defaultRuntime": {
    "runtimeType": "",
    "runtimePath": "",
    "runtimeEngine": "",
    "PodAnnotations": [],
    "ContainerAnnotations": [],
    "runtimeRoot": "",
    "options": {},
    "privileged_without_host_devices": false,
    "privileged_without_host_devices_all_devices_allowed": false,
    "baseRuntimeSpec": "",
    "cniConfDir": "",
    "cniMaxConfNum": 0,
    "snapshotter": "",
    "sandboxMode": ""
    },
    "untrustedWorkloadRuntime": {
    "runtimeType": "",
    "runtimePath": "",
    "runtimeEngine": "",
    "PodAnnotations": [],
    "ContainerAnnotations": [],
    "runtimeRoot": "",
    "options": {},
    "privileged_without_host_devices": false,
    "privileged_without_host_devices_all_devices_allowed": false,
    "baseRuntimeSpec": "",
    "cniConfDir": "",
    "cniMaxConfNum": 0,
    "snapshotter": "",
    "sandboxMode": ""
    },
    "runtimes": {
    "nvidia": {
    "runtimeType": "io.containerd.runc.v2",
    "runtimePath": "",
    "runtimeEngine": "",
    "PodAnnotations": null,
    "ContainerAnnotations": null,
    "runtimeRoot": "",
    "options": {
    "BinaryName": "/usr/bin/nvidia-container-runtime",
    "SystemdCgroup": true
    },
    "privileged_without_host_devices": false,
    "privileged_without_host_devices_all_devices_allowed": false,
    "baseRuntimeSpec": "",
    "cniConfDir": "",
    "cniMaxConfNum": 0,
    "snapshotter": "",
    "sandboxMode": "podsandbox"
    },
    "runc": {
    "runtimeType": "io.containerd.runc.v2",
    "runtimePath": "",
    "runtimeEngine": "",
    "PodAnnotations": [],
    "ContainerAnnotations": [],
    "runtimeRoot": "",
    "options": {
    "BinaryName": "",
    "CriuImagePath": "",
    "CriuPath": "",
    "CriuWorkPath": "",
    "IoGid": 0,
    "IoUid": 0,
    "NoNewKeyring": false,
    "NoPivotRoot": false,
    "Root": "",
    "ShimCgroup": "",
    "SystemdCgroup": true
    },
    "privileged_without_host_devices": false,
    "privileged_without_host_devices_all_devices_allowed": false,
    "baseRuntimeSpec": "",
    "cniConfDir": "",
    "cniMaxConfNum": 0,
    "snapshotter": "",
    "sandboxMode": "podsandbox"
    }
    },
    "noPivot": false,
    "disableSnapshotAnnotations": true,
    "discardUnpackedLayers": false,
    "ignoreBlockIONotEnabledErrors": false,
    "ignoreRdtNotEnabledErrors": false
    },
    "cni": {
    "binDir": "/opt/cni/bin",
    "confDir": "/etc/cni/net.d",
    "maxConfNum": 1,
    "setupSerially": false,
    "confTemplate": "",
    "ipPref": ""
    },
    "registry": {
    "configPath": "/etc/containerd/certs.d",
    "mirrors": null,
    "configs": null,
    "auths": null,
    "headers": null
    },
    "imageDecryption": {
    "keyModel": "node"
    },
    "disableTCPService": true,
    "streamServerAddress": "127.0.0.1",
    "streamServerPort": "0",
    "streamIdleTimeout": "4h0m0s",
    "enableSelinux": false,
    "selinuxCategoryRange": 1024,
    "sandboxImage": "xxx.xxx.xxx.xxx:10443/library/pause:3.7",
    "statsCollectPeriod": 10,
    "systemdCgroup": false,
    "enableTLSStreaming": false,
    "x509KeyPairStreaming": {
    "tlsCertFile": "",
    "tlsKeyFile": ""
    },
    "maxContainerLogSize": 16384,
    "disableCgroup": false,
    "disableApparmor": false,
    "restrictOOMScoreAdj": false,
    "maxConcurrentDownloads": 3,
    "disableProcMount": false,
    "unsetSeccompProfile": "",
    "tolerateMissingHugetlbController": true,
    "disableHugetlbController": true,
    "device_ownership_from_security_context": false,
    "ignoreImageDefinedVolumes": false,
    "netnsMountsUnderStateDir": false,
    "enableUnprivilegedPorts": false,
    "enableUnprivilegedICMP": false,
    "enableCDI": false,
    "cdiSpecDirs": [
    "/etc/cdi",
    "/var/run/cdi"
    ],
    "imagePullProgressTimeout": "1m0s",
    "drainExecSyncIOTimeout": "0s",
    "containerdRootDir": "/data/lib/containerd",
    "containerdEndpoint": "/run/containerd/containerd.sock",
    "rootDir": "/data/lib/containerd/io.containerd.grpc.v1.cri",
    "stateDir": "/run/containerd/io.containerd.grpc.v1.cri"
    },
    "golang": "go1.20.2",
    "lastCNILoadStatus": "OK",
    "lastCNILoadStatus.default": "OK"

    vllm版本:
    cr.metax-tech.com/public-ai-release/maca/vllm-metax:0.21.0-maca.ai3.7.1.106-torch2.8-py312-kylinv11-amd64

    启动命令:
    python3 -m vllm.entrypoints.openai.api_server --served-model-name Qwen3-30B-A3B-Instruct-2507 --model /model/Qwen3-30B-A3B-w8a8/ --port 8000 --tensor-parallel-size 1 --enable-prefix-caching --enable-auto-tool-choice --tool-call-parser hermes --default-chat-template-kwargs '{"enable_thinking":false}'

    英文输出正常,中文输出会夹带大量英文,有时候也会出现无限循环的情况

  • See post chevron_right
    GZZ
    Members
    显卡C500 64G 单卡部署 metax-tech/Qwen3-30B-A3B-W8A8 输出异常 已解决 2026年8月31日 10:44

    显卡C500 64G 单卡部署 metax-tech/Qwen3-30B-A3B-W8A8 metax-vllm版本0.21,部署后,英文输出正常,要求他中文回答的时候,里面仍然会有30%的英文输出,比如:我能够帮助you什么,你可以tell我,and you can 提供进一步的数据,我会help你

  • 沐曦开发者论坛
powered by misago