1. 从第三集过来，我们就可以开始实现飞书机器人功能了
2.实现的效果不错，很丝滑
3.飞书侧的配置
3.1 登录https://open.feishu.cn/app
3.2
3.3 飞书权限
json
{
"scopes": {
"tenant": [
"base:app:copy",
"base:app:create",
"base:app:read",
"base:app:update",
"base:collaborator:create",
"base:collaborator:delete",
"base:collaborator:read",
"base:dashboard:copy",
"base:dashboard:read",
"base:field:create",
"base:field:delete",
"base:field:read",
"base:field:update",
"base:form:read",
"base:form:update",
"base:record:create",
"base:record:delete",
"base:record:read",
"base:record:retrieve",
"base:record:update",
"base:role:create",
"base:role:delete",
"base:role:read",
"base:role:update",
"base:table:create",
"base:table:delete",
"base:table:read",
"base:table:update",
"base:view:read",
"base:view:write_only",
"bitable:app",
"bitable:app:readonly",
"board:whiteboard:node:create",
"board:whiteboard:node:delete",
"board:whiteboard:node:read",
"board:whiteboard:node:update",
"contact:contact.base:readonly",
"contact:user.base:readonly",
"contact:user.employee_id:readonly",
"contact:user.employee_number:read",
"contact:user.id:readonly",
"docs:doc",
"docs:doc:readonly",
"docs:document.comment:create",
"docs:document.comment:read",
"docs:document.comment:update",
"docs:document.comment:write_only",
"docs:document.content:read",
"docs:document.media:download",
"docs:document.media:upload",
"docs:document.subscription",
"docs:document.subscription:read",
"docs:document:copy",
"docs:document:export",
"docs:document:import",
"docs:event.document_deleted:read",
"docs:event.document_edited:read",
"docs:event.document_opened:read",
"docs:event:subscribe",
"docs:permission.member",
"docs:permission.member:auth",
"docs:permission.member:create",
"docs:permission.member:delete",
"docs:permission.member:readonly",
"docs:permission.member:retrieve",
"docs:permission.member:transfer",
"docs:permission.member:update",
"docs:permission.setting",
"docs:permission.setting:read",
"docs:permission.setting:readonly",
"docs:permission.setting:write_only",
"docx:document",
"docx:document.block:convert",
"docx:document:create",
"docx:document:readonly",
"drive:drive",
"drive:drive.metadata:readonly",
"drive:drive.search:readonly",
"drive:drive:readonly",
"drive:drive:version",
"drive:drive:version:readonly",
"drive:export:readonly",
"drive:file",
"drive:file.like:readonly",
"drive:file.meta.sec_label.read_only",
"drive:file:download",
"drive:file:readonly",
"drive:file:upload",
"drive:file:view_record:readonly",
"event:ip_list",
"im:app_feed_card:write",
"im:biz_entity_tag_relation:read",
"im:biz_entity_tag_relation:write",
"im:chat",
"im:chat.access_event.bot_p2p_chat:read",
"im:chat.announcement:read",
"im:chat.announcement:write_only",
"im:chat.chat_pins:read",
"im:chat.chat_pins:write_only",
"im:chat.collab_plugins:read",
"im:chat.collab_plugins:write_only",
"im:chat.managers:write_only",
"im:chat.members:bot_access",
"im:chat.members:read",
"im:chat.members:write_only",
"im:chat.menu_tree:read",
"im:chat.menu_tree:write_only",
"im:chat.moderation:read",
"im:chat.tabs:read",
"im:chat.tabs:write_only",
"im:chat.top_notice:write_only",
"im:chat.widgets:read",
"im:chat.widgets:write_only",
"im:chat:create",
"im:chat:delete",
"im:chat:moderation:write_only",
"im:chat:operate_as_owner",
"im:chat:read",
"im:chat:readonly",
"im:chat:update",
"im:datasync.feed_card.time_sensitive:write",
"im:message",
"im:message.group_at_msg:readonly",
"im:message.group_msg",
"im:message.p2p_msg:readonly",
"im:message.pins:read",
"im:message.pins:write_only",
"im:message.reactions:read",
"im:message.reactions:write_only",
"im:message.urgent",
"im:message.urgent.status:write",
"im:message.urgent:phone",
"im:message.urgent:sms",
"im:message:readonly",
"im:message:recall",
"im:message:send_as_bot",
"im:message:send_multi_depts",
"im:message:send_multi_users",
"im:message:send_sys_msg",
"im:message:update",
"im:resource",
"im:tag:read",
"im:tag:write",
"im:url_preview.update",
"im:user_agent:read",
"sheets:spreadsheet",
"sheets:spreadsheet.meta:read",
"sheets:spreadsheet.meta:write_only",
"sheets:spreadsheet:create",
"sheets:spreadsheet:read",
"sheets:spreadsheet:readonly",
"sheets:spreadsheet:write_only",
"space:document.event:read",
"space:document:delete",
"space:document:move",
"space:document:retrieve",
"space:document:shortcut",
"space:folder:create",
"wiki:member:create",
"wiki:member:retrieve",
"wiki:member:update",
"wiki:node:copy",
"wiki:node:create",
"wiki:node:move",
"wiki:node:read",
"wiki:node:retrieve",
"wiki:node:update",
"wiki:setting:read",
"wiki:setting:write_only",
"wiki:space:read",
"wiki:space:retrieve",
"wiki:space:write_only",
"wiki:wiki",
"wiki:wiki:readonly"
]
}
}
4.WSL侧的配置
4.1 openclaw的飞书配置
bash
(base) gpu3090@DESKTOP-8IU6393:~/openclaw$ openclaw onboard
Config warnings:\n- plugins.entries.feishu: plugin feishu: duplicate plugin id detected; later plugin may be overridden (/home/gpu3090/.nvm/versions/node/v22.12.0/lib/node_modules/openclaw/extensions/feishu/index.ts)
🦞 OpenClaw 2026.2.23 (b817600) --- Your messages, your servers, your control.
│
◇ Config warnings ────────────────────────────────────────────────────────────────────────────────────╮
│ │
│ - plugins.entries.feishu: plugin feishu: duplicate plugin id detected; later plugin may │
│ be overridden │
│ (/home/gpu3090/.nvm/versions/node/v22.12.0/lib/node_modules/openclaw/extensions/feishu/index.ts) │
│ │
├──────────────────────────────────────────────────────────────────────────────────────────────────────╯
│
◇ Doctor changes ────────────────────────────╮
│ │
│ feishu configured, enabled automatically. │
│ │
├─────────────────────────────────────────────╯
│
◇ Doctor ──────────────────────────────────────────────╮
│ │
│ Run "openclaw doctor --fix" to apply these changes. │
│ │
├───────────────────────────────────────────────────────╯
Config warnings:\n- plugins.entries.feishu: plugin feishu: duplicate plugin id detected; later plugin may be overridden (/home/gpu3090/.nvm/versions/node/v22.12.0/lib/node_modules/openclaw/extensions/feishu/index.ts)
12:00:52 [plugins] plugins.allow is empty; discovered non-bundled plugins may auto-load: feishu (/home/gpu3090/.openclaw/extensions/feishu/index.ts). Set plugins.allow to explicit trusted ids.
Config warnings:\n- plugins.entries.feishu: plugin feishu: duplicate plugin id detected; later plugin may be overridden (/home/gpu3090/.nvm/versions/node/v22.12.0/lib/node_modules/openclaw/extensions/feishu/index.ts)
12:01:01 [plugins] feishu_doc: Registered feishu_doc, feishu_app_scopes
12:01:01 [plugins] feishu_wiki: Registered feishu_wiki tool
12:01:01 [plugins] feishu_drive: Registered feishu_drive tool
12:01:01 [plugins] feishu_bitable: Registered bitable tools
12:01:01 [plugins] feishu: loaded without install/load-path provenance; treat as untracked local code and pin trust via plugins.allow or install records (/home/gpu3090/.openclaw/extensions/feishu/index.ts)
▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄
██░▄▄▄░██░▄▄░██░▄▄▄██░▀██░██░▄▄▀██░████░▄▄▀██░███░██
██░███░██░▀▀░██░▄▄▄██░█░█░██░█████░████░▀▀░██░█░█░██
██░▀▀▀░██░█████░▀▀▀██░██▄░██░▀▀▄██░▀▀░█░██░██▄▀▄▀▄██
▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀
🦞 OPENCLAW 🦞
┌ OpenClaw onboarding
│
◇ Security ──────────────────────────────────────────────────────────────────────────────╮
│ │
│ Security warning --- please read. │
│ │
│ OpenClaw is a hobby project and still in beta. Expect sharp edges. │
│ This bot can read files and run actions if tools are enabled. │
│ A bad prompt can trick it into doing unsafe things. │
│ │
│ If you're not comfortable with basic security and access control, don't run OpenClaw. │
│ Ask someone experienced to help before enabling tools or exposing it to the internet. │
│ │
│ Recommended baseline: │
│ - Pairing/allowlists + mention gating. │
│ - Sandbox + least-privilege tools. │
│ - Keep secrets out of the agent's reachable filesystem. │
│ - Use the strongest available model for any bot with tools or untrusted inboxes. │
│ │
│ Run regularly: │
│ openclaw security audit --deep │
│ openclaw security audit --fix │
│ │
│ Must read: https://docs.openclaw.ai/gateway/security │
│ │
├─────────────────────────────────────────────────────────────────────────────────────────╯
│
◇ I understand this is powerful and inherently risky. Continue?
│ Yes
│
◇ Onboarding mode
│ QuickStart
│
◇ Existing config detected ─────────╮
│ │
│ workspace: ~/.openclaw/workspace │
│ model: ollama/gpt-oss:20b │
│ gateway.mode: local │
│ gateway.port: 18789 │
│ gateway.bind: loopback │
│ │
├────────────────────────────────────╯
│
◇ Config handling
│ Use existing values
│
◇ QuickStart ─────────────────────────────╮
│ │
│ Keeping your current gateway settings: │
│ Gateway port: 18789 │
│ Gateway bind: Loopback (127.0.0.1) │
│ Gateway auth: Token (default) │
│ Tailscale exposure: Off │
│ Direct to chat channels. │
│ │
├──────────────────────────────────────────╯
Config warnings:\n- plugins.entries.feishu: plugin feishu: duplicate plugin id detected; later plugin may be overridden (/home/gpu3090/.nvm/versions/node/v22.12.0/lib/node_modules/openclaw/extensions/feishu/index.ts)
│
◇ Model/auth provider
│ Skip for now
│
◇ Filter models by provider
│ ollama
│
◇ Default model
│ Keep current (ollama/gpt-oss:20b)
[info]: [ 'client ready' ]
│
◇ Channel status ───────────────────────────────────────────╮
│ │
│ Telegram: needs token │
│ Feishu: connected as ou_eb8c5e1d04bc3f409c348066f53b7aed │
│ WhatsApp: not configured │
│ Discord: not configured │
│ IRC: not configured │
│ Google Chat: not configured │
│ Slack: not configured │
│ Signal: not configured │
│ iMessage: not configured │
│ Google Chat: install plugin to enable │
│ Nostr: install plugin to enable │
│ Microsoft Teams: install plugin to enable │
│ Mattermost: install plugin to enable │
│ Nextcloud Talk: install plugin to enable │
│ Matrix: install plugin to enable │
│ BlueBubbles: install plugin to enable │
│ LINE: install plugin to enable │
│ Zalo: install plugin to enable │
│ Zalo Personal: install plugin to enable │
│ Synology Chat: install plugin to enable │
│ Tlon: install plugin to enable │
│ │
├────────────────────────────────────────────────────────────╯
│
◇ How channels work ───────────────────────────────────────────────────────────────────────╮
│ │
│ DM security: default is pairing; unknown DMs get a pairing code. │
│ Approve with: openclaw pairing approve <channel> <code> │
│ Public DMs require dmPolicy="open" + allowFrom=["*"]. │
│ Multi-user DMs: run: openclaw config set session.dmScope "per-channel-peer" (or │
│ "per-account-channel-peer" for multi-account channels) to isolate sessions. │
│ Docs: channels/pairing │
│ │
│ Telegram: simplest way to get started --- register a bot with @BotFather and get going. │
│ WhatsApp: works with your own number; recommend a separate phone + eSIM. │
│ Discord: very well supported right now. │
│ IRC: classic IRC networks with DM/channel routing and pairing controls. │
│ Google Chat: Google Workspace Chat app with HTTP webhook. │
│ Slack: supported (Socket Mode). │
│ Signal: signal-cli linked device; more setup (David Reagans: "Hop on Discord."). │
│ iMessage: this is still a work in progress. │
│ Feishu: 飞书/Lark enterprise messaging. │
│ Nostr: Decentralized protocol; encrypted DMs via NIP-04. │
│ Microsoft Teams: Bot Framework; enterprise support. │
│ Mattermost: self-hosted Slack-style chat; install the plugin to enable. │
│ Nextcloud Talk: Self-hosted chat via Nextcloud Talk webhook bots. │
│ Matrix: open protocol; install the plugin to enable. │
│ BlueBubbles: iMessage via the BlueBubbles mac app + REST API. │
│ LINE: LINE Messaging API bot for Japan/Taiwan/Thailand markets. │
│ Zalo: Vietnam-focused messaging platform with Bot API. │
│ Zalo Personal: Zalo personal account via QR code login. │
│ Synology Chat: Connect your Synology NAS Chat to OpenClaw with full agent capabilities. │
│ Tlon: decentralized messaging on Urbit; install the plugin to enable. │
│ │
├───────────────────────────────────────────────────────────────────────────────────────────╯
│
◇ Select channel (QuickStart)
│ Feishu/Lark (飞书)
│
◇ Feishu already configured. What do you want to do?
│ Skip (leave as-is)
Config warnings:
- plugins.entries.feishu: plugin feishu: duplicate plugin id detected; later plugin may be overridden (/home/gpu3090/.nvm/versions/node/v22.12.0/lib/node_modules/openclaw/extensions/feishu/index.ts)
Config overwrite: /home/gpu3090/.openclaw/openclaw.json (sha256 383fc01adf5e6d22ff26c8a88e7daab8bdfd4a4380a983c8ec9aef6f9cb67caa -> 3c519fdbdc2ae58df8890e1c8490567bb0287aa70fd50aef0c1ed9d815be14e7, backup=/home/gpu3090/.openclaw/openclaw.json.bak)
Updated ~/.openclaw/openclaw.json
Workspace OK: ~/.openclaw/workspace
Sessions OK: ~/.openclaw/agents/main/sessions
│
◇ Skills status ─────────────╮
│ │
│ Eligible: 10 │
│ Missing requirements: 38 │
│ Unsupported on this OS: 7 │
│ Blocked by allowlist: 0 │
│ │
├─────────────────────────────╯
│
◇ Configure skills now? (recommended)
│ No
│
◇ Hooks ──────────────────────────────────────────────────────────────────╮
│ │
│ Hooks let you automate actions when agent commands are issued. │
│ Example: Save session context to memory when you issue /new or /reset. │
│ │
│ Learn more: https://docs.openclaw.ai/automation/hooks │
│ │
├──────────────────────────────────────────────────────────────────────────╯
│
◇ Enable hooks?
│ Skip for now
Config warnings:
- plugins.entries.feishu: plugin feishu: duplicate plugin id detected; later plugin may be overridden (/home/gpu3090/.nvm/versions/node/v22.12.0/lib/node_modules/openclaw/extensions/feishu/index.ts)
Config overwrite: /home/gpu3090/.openclaw/openclaw.json (sha256 3c519fdbdc2ae58df8890e1c8490567bb0287aa70fd50aef0c1ed9d815be14e7 -> bd6eabd7f470daa88d0ccec4be9099659f7872174a9ee6265f3ca866a5d5adf0, backup=/home/gpu3090/.openclaw/openclaw.json.bak)
│
◇ Systemd ───────────────────────────────────────────────────────────────────────────────╮
│ │
│ Systemd user services are unavailable. Skipping lingering checks and service install. │
│ │
├─────────────────────────────────────────────────────────────────────────────────────────╯
Config warnings:\n- plugins.entries.feishu: plugin feishu: duplicate plugin id detected; later plugin may be overridden (/home/gpu3090/.nvm/versions/node/v22.12.0/lib/node_modules/openclaw/extensions/feishu/index.ts)
│
◇
Feishu: ok
Agents: main (default)
Heartbeat interval: 30m (main)
Session store (main): /home/gpu3090/.openclaw/agents/main/sessions/sessions.json (1 entries)
- agent:main:main (1m ago)
│
◇ Optional apps ────────────────────────╮
│ │
│ Add nodes for extra features: │
│ - macOS app (system + notifications) │
│ - iOS app (camera/canvas) │
│ - Android app (camera/canvas) │
│ │
├────────────────────────────────────────╯
│
◇ Control UI ─────────────────────────────────────────────────────────────────────╮
│ │
│ Web UI: http://127.0.0.1:18789/ │
│ Web UI (with token): │
│ http://127.0.0.1:18789/#token=653d40aee8d790919cd740786a2bc5f6b41b3ef0b20ee905 │
│ Gateway WS: ws://127.0.0.1:18789 │
│ Gateway: reachable │
│ Docs: https://docs.openclaw.ai/web/control-ui │
│ │
├──────────────────────────────────────────────────────────────────────────────────╯
│
◇ Start TUI (best option!) ─────────────────────────────────╮
│ │
│ This is the defining action that makes your agent you. │
│ Please take your time. │
│ The more you tell it, the better the experience will be. │
│ We will send: "Wake up, my friend!" │
│ │
├────────────────────────────────────────────────────────────╯
│
◇ Token ─────────────────────────────────────────────────────────────────────────────────╮
│ │
│ Gateway token: shared auth for the Gateway + Control UI. │
│ Stored in: ~/.openclaw/openclaw.json (gateway.auth.token) or OPENCLAW_GATEWAY_TOKEN. │
│ View token: openclaw config get gateway.auth.token │
│ Generate token: openclaw doctor --generate-gateway-token │
│ Web UI stores a copy in this browser's localStorage (openclaw.control.settings.v1). │
│ Open the dashboard anytime: openclaw dashboard --no-open │
│ If prompted: paste the token into Control UI settings (or use the tokenized dashboard │
│ URL). │
│ │
├─────────────────────────────────────────────────────────────────────────────────────────╯
│
◇ How do you want to hatch your bot?
│ Open the Web UI
│
◇ Dashboard ready ────────────────────────────────────────────────────────────────╮
│ │
│ Dashboard link (with token): │
│ http://127.0.0.1:18789/#token=653d40aee8d790919cd740786a2bc5f6b41b3ef0b20ee905 │
│ Copy/paste this URL in a browser on this machine to control OpenClaw. │
│ No GUI detected. Open from your computer: │
│ ssh -N -L 18789:127.0.0.1:18789 gpu3090@<host> │
│ Then open: │
│ http://localhost:18789/ │
│ http://localhost:18789/#token=653d40aee8d790919cd740786a2bc5f6b41b3ef0b20ee905 │
│ Docs: │
│ https://docs.openclaw.ai/gateway/remote │
│ https://docs.openclaw.ai/web/control-ui │
│ │
├──────────────────────────────────────────────────────────────────────────────────╯
│
◇ Workspace backup ────────────────────────────────────────╮
│ │
│ Back up your agent workspace. │
│ Docs: https://docs.openclaw.ai/concepts/agent-workspace │
│ │
├───────────────────────────────────────────────────────────╯
│
◇ Security ──────────────────────────────────────────────────────╮
│ │
│ Running agents on your computer is risky --- harden your setup: │
│ https://docs.openclaw.ai/security │
│ │
├─────────────────────────────────────────────────────────────────╯
│
◇ Web search (optional) ─────────────────────────────────────────────────────────────────╮
│ │
│ If you want your agent to be able to search the web, you'll need an API key. │
│ │
│ OpenClaw uses Brave Search for the `web_search` tool. Without a Brave Search API key, │
│ web search won't work. │
│ │
│ Set it up interactively: │
│ - Run: openclaw configure --section web │
│ - Enable web_search and paste your Brave Search API key │
│ │
│ Alternative: set BRAVE_API_KEY in the Gateway environment (no config changes). │
│ Docs: https://docs.openclaw.ai/tools/web │
│ │
├─────────────────────────────────────────────────────────────────────────────────────────╯
│
◇ What now ─────────────────────────────────────────────────────────────╮
│ │
│ What now: https://openclaw.ai/showcase ("What People Are Building"). │
│ │
├────────────────────────────────────────────────────────────────────────╯
│
└ Onboarding complete. Use the dashboard link above to control OpenClaw.
(base) gpu3090@DESKTOP-8IU6393:~/openclaw$ openclaw pairing approve feishu ZMBRUDJ8
Config warnings:\n- plugins.entries.feishu: plugin feishu: duplicate plugin id detected; later plugin may be overridden (/home/gpu3090/.nvm/versions/node/v22.12.0/lib/node_modules/openclaw/extensions/feishu/index.ts)
12:06:02 [plugins] plugins.allow is empty; discovered non-bundled plugins may auto-load: feishu (/home/gpu3090/.openclaw/extensions/feishu/index.ts). Set plugins.allow to explicit trusted ids.
Config warnings:\n- plugins.entries.feishu: plugin feishu: duplicate plugin id detected; later plugin may be overridden (/home/gpu3090/.nvm/versions/node/v22.12.0/lib/node_modules/openclaw/extensions/feishu/index.ts)
12:06:04 [plugins] feishu_doc: Registered feishu_doc, feishu_app_scopes
12:06:04 [plugins] feishu_wiki: Registered feishu_wiki tool
12:06:04 [plugins] feishu_drive: Registered feishu_drive tool
12:06:04 [plugins] feishu_bitable: Registered bitable tools
12:06:04 [plugins] feishu: loaded without install/load-path provenance; treat as untracked local code and pin trust via plugins.allow or install records (/home/gpu3090/.openclaw/extensions/feishu/index.ts)
🦞 OpenClaw 2026.2.23 (b817600) --- End-to-end encrypted, drama-to-drama excluded.
│
◇ Config warnings ────────────────────────────────────────────────────────────────────────────────────╮
│ │
│ - plugins.entries.feishu: plugin feishu: duplicate plugin id detected; later plugin may │
│ be overridden │
│ (/home/gpu3090/.nvm/versions/node/v22.12.0/lib/node_modules/openclaw/extensions/feishu/index.ts) │
│ │
├──────────────────────────────────────────────────────────────────────────────────────────────────────╯
│
◇ Doctor changes ────────────────────────────╮
│ │
│ feishu configured, enabled automatically. │
│ │
├─────────────────────────────────────────────╯
│
◇ Doctor ──────────────────────────────────────────────╮
│ │
│ Run "openclaw doctor --fix" to apply these changes. │
│ │
├───────────────────────────────────────────────────────╯
Approved feishu sender ou_ca33d772eb1cdf7fd9dbfa225f53ce4d.启动ollama里面的大模型
bash
PS C:\Users\Administrator> wsl -u gpu3090
Now using node v22.12.0 (npm v10.9.0)
(base) gpu3090@DESKTOP-8IU6393:/mnt/c/Users/Administrator$ cd
(base) gpu3090@DESKTOP-8IU6393:~$ OLLAMA_HOST=0.0.0.0:12346 OLLAMA_MODELS=/home/gpu3090/.ollama/models ollama serve &
[1] 15030
(base) gpu3090@DESKTOP-8IU6393:~$ time=2026-02-24T20:10:33.806+08:00 level=INFO source=routes.go:1663 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY:http://127.0.0.1:7897 HTTP_PROXY:http://127.0.0.1:7897 NO_PROXY:172.31.*,172.30.*,172.29.*,172.28.*,172.27.*,172.26.*,172.25.*,172.24.*,172.23.*,172.22.*,172.21.*,172.20.*,172.19.*,172.18.*,172.17.*,172.16.*,10.*,192.168.*,127.*,localhost,<local> OLLAMA_CONTEXT_LENGTH:0 OLLAMA_DEBUG:INFO OLLAMA_EDITOR: OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:12346 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/gpu3090/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NO_CLOUD:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy:http://127.0.0.1:7897 https_proxy:http://127.0.0.1:7897 no_proxy:172.31.*,172.30.*,172.29.*,172.28.*,172.27.*,172.26.*,172.25.*,172.24.*,172.23.*,172.22.*,172.21.*,172.20.*,172.19.*,172.18.*,172.17.*,172.16.*,10.*,192.168.*,127.*,localhost,<local>]"
time=2026-02-24T20:10:33.810+08:00 level=INFO source=routes.go:1665 msg="Ollama cloud disabled: false"
time=2026-02-24T20:10:34.150+08:00 level=INFO source=images.go:473 msg="total blobs: 53"
time=2026-02-24T20:10:34.313+08:00 level=INFO source=images.go:480 msg="total unused blobs removed: 0"
time=2026-02-24T20:10:34.458+08:00 level=INFO source=routes.go:1718 msg="Listening on [::]:12346 (version 0.16.3)"
time=2026-02-24T20:10:34.473+08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2026-02-24T20:10:34.502+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 46037"
time=2026-02-24T20:10:36.614+08:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN=1"
time=2026-02-24T20:10:36.615+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 46237"
time=2026-02-24T20:10:38.176+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 46265"
time=2026-02-24T20:10:38.186+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 45607"
time=2026-02-24T20:10:38.416+08:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-67135303-3c02-f35c-3e58-dc2c1b4892fc filter_id="" library=CUDA compute=8.9 name=CUDA0 description="NVIDIA GeForce RTX 4090 D" libdirs=ollama,cuda_v13 driver=13.0 pci_id=0000:07:00.0 type=discrete total="24.0 GiB" available="20.5 GiB"
time=2026-02-24T20:10:38.416+08:00 level=INFO source=routes.go:1768 msg="vram-based default context" total_vram="24.0 GiB" default_num_ctx=32768
time=2026-02-24T20:10:55.284+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 45515"
time=2026-02-24T20:10:55.902+08:00 level=INFO source=server.go:247 msg="enabling flash attention"
time=2026-02-24T20:10:55.903+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --model /home/gpu3090/.ollama/models/blobs/sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb --port 46267"
time=2026-02-24T20:10:55.903+08:00 level=INFO source=sched.go:491 msg="system memory" total="62.7 GiB" free="60.9 GiB" free_swap="16.0 GiB"
time=2026-02-24T20:10:55.903+08:00 level=INFO source=sched.go:498 msg="gpu memory" id=GPU-67135303-3c02-f35c-3e58-dc2c1b4892fc library=CUDA available="20.1 GiB" free="20.5 GiB" minimum="457.0 MiB" overhead="0 B"
time=2026-02-24T20:10:55.903+08:00 level=INFO source=server.go:757 msg="loading model" "model layers"=25 requested=-1
time=2026-02-24T20:10:55.919+08:00 level=INFO source=runner.go:1411 msg="starting ollama engine"
time=2026-02-24T20:10:55.941+08:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:46267"
time=2026-02-24T20:10:55.949+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:32768 KvCacheType: NumThreads:12 GPULayers:25[ID:GPU-67135303-3c02-f35c-3e58-dc2c1b4892fc Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-24T20:10:56.075+08:00 level=INFO source=ggml.go:136 msg="" architecture=gptoss file_type=MXFP4 name="" description="" num_tensors=459 num_key_values=32
load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 4090 D, compute capability 8.9, VMM: yes, ID: GPU-67135303-3c02-f35c-3e58-dc2c1b4892fc
load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v13/libggml-cuda.so
time=2026-02-24T20:10:56.244+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)
time=2026-02-24T20:10:58.623+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:32768 KvCacheType: NumThreads:12 GPULayers:25[ID:GPU-67135303-3c02-f35c-3e58-dc2c1b4892fc Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:32768 KvCacheType: NumThreads:12 GPULayers:25[ID:GPU-67135303-3c02-f35c-3e58-dc2c1b4892fc Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=ggml.go:482 msg="offloading 24 repeating layers to GPU"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=ggml.go:494 msg="offloaded 25/25 layers to GPU"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="11.8 GiB"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="1.1 GiB"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="876.0 MiB"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="202.3 MiB"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=device.go:272 msg="total memory" size="13.9 GiB"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=sched.go:566 msg="loaded runners" count=1
time=2026-02-24T20:10:59.089+08:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding"
time=2026-02-24T20:10:59.090+08:00 level=INFO source=server.go:1384 msg="waiting for server to become available" status="llm server loading model"
time=2026-02-24T20:13:29.638+08:00 level=INFO source=server.go:1388 msg="llama runner started in 150.89 seconds"
[GIN] 2026/02/24 - 20:13:33 | 200 | 2m36s | 127.0.0.1 | POST "/v1/chat/completions"
[GIN] 2026/02/24 - 20:14:13 | 200 | 2.66893432s | 127.0.0.1 | POST "/v1/chat/completions"
[GIN] 2026/02/24 - 20:14:15 | 200 | 1.55337028s | 127.0.0.1 | POST "/v1/chat/completions"
[GIN] 2026/02/24 - 20:14:19 | 200 | 3.807682829s | 127.0.0.1 | POST "/v1/chat/completions"
[GIN] 2026/02/24 - 20:16:44 | 200 | 4.57320368s | 127.0.0.1 | POST "/v1/chat/completions"
ggml_backend_cuda_device_get_memory device GPU-67135303-3c02-f35c-3e58-dc2c1b4892fc utilizing NVML memory reporting free: 7589896192 total: 25757220864
time=2026-02-24T20:21:55.251+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 46347"
time=2026-02-24T20:23:16.264+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 44657"
time=2026-02-24T20:23:16.818+08:00 level=INFO source=server.go:247 msg="enabling flash attention"
time=2026-02-24T20:23:16.819+08:00 level=INFO source=server.go:431 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --model /home/gpu3090/.ollama/models/blobs/sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb --port 44781"
time=2026-02-24T20:23:16.820+08:00 level=INFO source=sched.go:491 msg="system memory" total="62.7 GiB" free="60.9 GiB" free_swap="16.0 GiB"
time=2026-02-24T20:23:16.820+08:00 level=INFO source=sched.go:498 msg="gpu memory" id=GPU-67135303-3c02-f35c-3e58-dc2c1b4892fc library=CUDA available="20.0 GiB" free="20.4 GiB" minimum="457.0 MiB" overhead="0 B"