[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DFVXC7AB45Z7F1JE5BST5R":3,"skill-same:01M6DFVXC7AB45Z7F1JE5BST5R":83},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":6,"ownerHtmlUrl":60,"ownerBlogUrl":6,"ownerDescription":61,"updatedAt":62,"install":63,"resources":76},"01M6DFVXC7AB45Z7F1JE5BST5R","freellmapi-free-tier",null,"Setup FreeLLMAPI free-tier routing for Hermes.","zapabob\u002FSkills","zapabob","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F130830376?v=4","01M6DBMYZAGRTFQDSQYW3W764P","峯岸 亮","01M6DBMZ3GKDSJ01NZ9XTZD7JD",2,"MIT","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F53\u002F53b2bea41fba857fecf315442ffbbef4e34e024eaddea8127e09239d46566bda\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"free","freellmapi free tier","macos","linux","windows","setup","routing","proxy","hermes","hermes agent","autonomous","opencode","AI-agents","free-tier","bob","local","2026-11-10 10:12:30",false,"---\nname: freellmapi-free-tier\ndescription: \"Setup FreeLLMAPI free-tier routing for Hermes.\"\nversion: 1.0.0\nauthor: Bob Nyan, Hermes Agent\nlicense: MIT\nplatforms: [linux, macos, windows]\nmetadata:\n  hermes:\n    tags: [FreeLLMAPI, Free-Tier, Failover, Routing, Local-Proxy]\n    category: autonomous-ai-agents\n    related_skills: [opencode-free-rotation, hermes-agent]\n---\n\n# FreeLLMAPI Free Tier Skill\n\nWire Hermes to a local [FreeLLMAPI](https:\u002F\u002Fgithub.com\u002Ftashfeenahmed\u002Ffreellmapi) proxy so ~16 free provider tiers share one OpenAI-compatible endpoint. The proxy rotates on 429\u002F5xx internally; Hermes adds a second failover layer via `fallback_providers`.\n\n## When to Use\n\n- You want Hermes on stacked free LLM tiers without managing 16 API keys in the agent\n- FreeLLMAPI is (or will be) running locally on `:3001`, exposed via **Tailscale**\n  at `https:\u002F\u002F\u003CTAILSCALE_DNS_NAME>\u002Ffreellmapi\u002Fv1` (not raw `127.0.0.1` from remote agents)\n- You need setup, doctor checks, or fallback-chain wiring after installing the bundled plugin\n\n## Prerequisites\n\n- Hermes checkout with `plugins\u002Fmodel-providers\u002Ffreellmapi\u002F` and `plugins\u002Ffreellmapi\u002F`\n- FreeLLMAPI running locally (Docker, desktop `.exe`, or `npm run dev`)\n- Unified API key from the FreeLLMAPI dashboard → `FREELLMAPI_API_KEY` in `~\u002F.hermes\u002F.env`\n- Optional: upstream provider keys added inside FreeLLMAPI (Google, Groq, OpenRouter free, etc.)\n\n## How to Run\n\n1. Enable the integration plugin and wire fallback:\n\n```\nterminal(command=\"hermes freellmapi setup\")\n```\n\n2. Run health checks (models probe when the API key is set):\n\n```\nterminal(command=\"hermes freellmapi doctor\")\n```\n\n3. Optional — make FreeLLMAPI the primary model backend:\n\n```\nterminal(command=\"hermes freellmapi setup --apply-model\")\n```\n\n4. Confirm Hermes-wide diagnostics:\n\n```\nterminal(command=\"hermes doctor\")\n```\n\n## Quick Reference\n\n| Action | Command |\n|--------|---------|\n| Enable plugin + fallback | `hermes freellmapi setup` |\n| Set primary provider | `hermes freellmapi setup --apply-model` |\n| Plugin-only status | `hermes freellmapi status` |\n| Deep probe | `hermes freellmapi doctor` |\n| Enable allow-list entry | `hermes plugins enable freellmapi` |\n\n## Procedure\n\n### 1. Install and start FreeLLMAPI\n\n**Docker (Linux\u002FmacOS\u002FWSL):**\n\n```\nterminal(command=\"curl -fsSL https:\u002F\u002Ffreellmapi.co\u002Finstall.sh | bash\")\n```\n\n**Windows:** install the `.exe` from [FreeLLMAPI Releases](https:\u002F\u002Fgithub.com\u002Ftashfeenahmed\u002Ffreellmapi\u002Freleases\u002Flatest).\n\nOpen `http:\u002F\u002Flocalhost:3001`, add upstream provider keys on **Keys**, reorder **Fallback Chain**, copy the unified `freellmapi-…` bearer token.\n\nExpose the local proxy on tailnet (required for this workspace — do not point Hermes at raw `127.0.0.1` from remote agents):\n\n```\nterminal(command=\"tailscale serve --bg --set-path=\u002Ffreellmapi\u002Fv1 http:\u002F\u002F127.0.0.1:3001\u002Fv1\")\nterminal(command=\"tailscale serve status\")\n```\n\n### 2. Store credentials\n\nAdd to `~\u002F.hermes\u002F.env` (secrets only):\n\n```\nFREELLMAPI_API_KEY=[REDACTED]\nFREELLMAPI_BASE_URL=https:\u002F\u002Fdownl.taile4f666.ts.net\u002Ffreellmapi\u002Fv1\n```\n\n### 3. Enable Hermes plugin\n\n```\nterminal(command=\"hermes plugins enable freellmapi\")\nterminal(command=\"hermes freellmapi setup\")\n```\n\nExpected: `freellmapi` appears in `plugins.enabled`; `fallback_providers[0]` becomes `{provider: freellmapi, model: auto}`.\n\n### 4. Recommended config\n\n```yaml\nmodel:\n  provider: freellmapi\n  default: auto\n  base_url: https:\u002F\u002Fdownl.taile4f666.ts.net\u002Ffreellmapi\u002Fv1\n\nfallback_providers:\n  - provider: freellmapi\n    model: auto\n  - provider: opencode-zen\n    model: auto-free\n```\n\nUse `read_file` on `~\u002F.hermes\u002Fconfig.yaml` before editing. Apply with `hermes freellmapi setup --apply-model` or `patch`.\n\n### 5. Verify routing\n\n```\nterminal(command=\"hermes freellmapi doctor\")\nterminal(command=\"hermes doctor\")\n```\n\nStart a short chat. FreeLLMAPI responses include `X-Routed-Via` \u002F `X-Fallback-Attempts` headers when probed with `terminal` + curl.\n\n## Pitfalls\n\n- FreeLLMAPI must be running before `doctor` can pass the models probe — connection refused is expected when the container is stopped.\n- The unified key is **not** an upstream Google\u002FGroq key; upstream keys live only inside FreeLLMAPI.\n- `model.provider: freellmapi` without `FREELLMAPI_API_KEY` fails at runtime — doctor catches this early.\n- Free tiers are for personal experimentation; do not expect production SLA.\n- On Windows native Hermes, prefer the desktop `.exe` or WSL Docker over binding Docker to LAN unless you trust the network.\n\n## Verification\n\n- `hermes freellmapi doctor` → `model_provider_profile` and `plugin_enabled` checks pass\n- With key + running proxy → `models_probe` ok and `model_count` > 0\n- `hermes doctor` shows no blocking errors for the active provider\n- Multi-turn sessions send `X-Session-Id` (sticky 30 min) via the bundled model-provider profile\n\n## Optional: context handoff on model switch\n\nIn FreeLLMAPI `.env`:\n\n```\nFREELLMAPI_CONTEXT_HANDOFF=on_model_switch\n```\n\nInjects one compact system message when the proxy falls over to a different upstream model mid-conversation.\n","# FreeLLMAPI Free Tier Skill\n\nWire Hermes to a local [FreeLLMAPI](https:\u002F\u002Fgithub.com\u002Ftashfeenahmed\u002Ffreellmapi) proxy so ~16 free provider tiers share one OpenAI-compatible endpoint. The proxy rotates on 429\u002F5xx internally; Hermes adds a second failover layer via `fallback_providers`.\n\n## When to Use\n\n- You want Hermes on stacked free LLM tiers without managing 16 API keys in the agent\n- FreeLLMAPI is (or will be) running locally on `:3001`, exposed via **Tailscale**\n  at `https:\u002F\u002F\u003CTAILSCALE_DNS_NAME>\u002Ffreellmapi\u002Fv1` (not raw `127.0.0.1` from remote agents)\n- You need setup, doctor checks, or fallback-chain wiring after installing the bundled plugin\n\n## Prerequisites\n\n- Hermes checkout with `plugins\u002Fmodel-providers\u002Ffreellmapi\u002F` and `plugins\u002Ffreellmapi\u002F`\n- FreeLLMAPI running locally (Docker, desktop `.exe`, or `npm run dev`)\n- Unified API key from the FreeLLMAPI dashboard → `FREELLMAPI_API_KEY` in `~\u002F.hermes\u002F.env`\n- Optional: upstream provider keys added inside FreeLLMAPI (Google, Groq, OpenRouter free, etc.)\n\n## How to Run\n\n1. Enable the integration plugin and wire fallback:\n\n```\nterminal(command=\"hermes freellmapi setup\")\n```\n\n2. Run health checks (models probe when the API key is set):\n\n```\nterminal(command=\"hermes freellmapi doctor\")\n```\n\n3. Optional — make FreeLLMAPI the primary model backend:\n\n```\nterminal(command=\"hermes freellmapi setup --apply-model\")\n```\n\n4. Confirm Hermes-wide diagnostics:\n\n```\nterminal(command=\"hermes doctor\")\n```\n\n## Quick Reference\n\n| Action | Command |\n|--------|---------|\n| Enable plugin + fallback | `hermes freellmapi setup` |\n| Set primary provider | `hermes freellmapi setup --apply-model` |\n| Plugin-only status | `hermes freellmapi status` |\n| Deep probe | `hermes freellmapi doctor` |\n| Enable allow-list entry | `hermes plugins enable freellmapi` |\n\n## Procedure\n\n### 1. Install and start FreeLLMAPI\n\n**Docker (Linux\u002FmacOS\u002FWSL):**\n\n```\nterminal(command=\"curl -fsSL https:\u002F\u002Ffreellmapi.co\u002Finstall.sh | bash\")\n```\n\n**Windows:** install the `.exe` from [FreeLLMAPI Releases](https:\u002F\u002Fgithub.com\u002Ftashfeenahmed\u002Ffreellmapi\u002Freleases\u002Flatest).\n\nOpen `http:\u002F\u002Flocalhost:3001`, add upstream provider keys on **Keys**, reorder **Fallback Chain**, copy the unified `freellmapi-…` bearer token.\n\nExpose the local proxy on tailnet (required for this workspace — do not point Hermes at raw `127.0.0.1` from remote agents):\n\n```\nterminal(command=\"tailscale serve --bg --set-path=\u002Ffreellmapi\u002Fv1 http:\u002F\u002F127.0.0.1:3001\u002Fv1\")\nterminal(command=\"tailscale serve status\")\n```\n\n### 2. Store credentials\n\nAdd to `~\u002F.hermes\u002F.env` (secrets only):\n\n```\nFREELLMAPI_API_KEY=[REDACTED]\nFREELLMAPI_BASE_URL=https:\u002F\u002Fdownl.taile4f666.ts.net\u002Ffreellmapi\u002Fv1\n```\n\n### 3. Enable Hermes plugin\n\n```\nterminal(command=\"hermes plugins enable freellmapi\")\nterminal(command=\"hermes freellmapi setup\")\n```\n\nExpected: `freellmapi` appears in `plugins.enabled`; `fallback_providers[0]` becomes `{provider: freellmapi, model: auto}`.\n\n### 4. Recommended config\n\n```yaml\nmodel:\n  provider: freellmapi\n  default: auto\n  base_url: https:\u002F\u002Fdownl.taile4f666.ts.net\u002Ffreellmapi\u002Fv1\n\nfallback_providers:\n  - provider: freellmapi\n    model: auto\n  - provider: opencode-zen\n    model: auto-free\n```\n\nUse `read_file` on `~\u002F.hermes\u002Fconfig.yaml` before editing. Apply with `hermes freellmapi setup --apply-model` or `patch`.\n\n### 5. Verify routing\n\n```\nterminal(command=\"hermes freellmapi doctor\")\nterminal(command=\"hermes doctor\")\n```\n\nStart a short chat. FreeLLMAPI responses include `X-Routed-Via` \u002F `X-Fallback-Attempts` headers when probed with `terminal` + curl.\n\n## Pitfalls\n\n- FreeLLMAPI must be running before `doctor` can pass the models probe — connection refused is expected when the container is stopped.\n- The unified key is **not** an upstream Google\u002FGroq key; upstream keys live only inside FreeLLMAPI.\n- `model.provider: freellmapi` without `FREELLMAPI_API_KEY` fails at runtime — doctor catches this early.\n- Free tiers are for personal experimentation; do not expect production SLA.\n- On Windows native Hermes, prefer the desktop `.exe` or WSL Docker over binding Docker to LAN unless you trust the network.\n\n## Verification\n\n- `hermes freellmapi doctor` → `model_provider_profile` and `plugin_enabled` checks pass\n- With key + running proxy → `models_probe` ok and `model_count` > 0\n- `hermes doctor` shows no blocking errors for the active provider\n- Multi-turn sessions send `X-Session-Id` (sticky 30 min) via the bundled model-provider profile\n\n## Optional: context handoff on model switch\n\nIn FreeLLMAPI `.env`:\n\n```\nFREELLMAPI_CONTEXT_HANDOFF=on_model_switch\n```\n\nInjects one compact system message when the proxy falls over to a different upstream model mid-conversation.\n",{"name":5,"author":40,"license":15,"version":41,"metadata":42,"platforms":54,"description":7},"Bob Nyan, Hermes Agent","1.0.0",{"hermes":43},{"tags":44,"category":50,"related_skills":51},[45,46,47,48,49],"FreeLLMAPI","Free-Tier","Failover","Routing","Local-Proxy","autonomous-ai-agents",[52,53],"opencode-free-rotation","hermes-agent",[22,21,23],"main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002F53\u002F53b2bea41fba857fecf315442ffbbef4e34e024eaddea8127e09239d46566bda",0,"https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills","https:\u002F\u002Fgithub.com\u002Fzapabob","The Open University of JAPAN　2019-now\r\n\r\nTokyo University of Science　2007-2010","2026-10-26 16:29:01",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add zapabob\u002FSkills --skill freellmapi-free-tier",{"tool":69,"command":70},"bunx","bunx skills add zapabob\u002FSkills --skill freellmapi-free-tier",{"tool":72,"command":73},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill freellmapi-free-tier","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F53\u002F53b2bea41fba857fecf315442ffbbef4e34e024eaddea8127e09239d46566bda\u002FSKILL.md",true,[77],{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"scripts\u002Famazon_best_selling_products_finder_api.py","SCRIPT","脚本",4097,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fdevops-cloud-operations\u002Fbrowser-automation-reference\u002Famazon-best-selling-products-finder-api-skill\u002Fscripts\u002Famazon_best_selling_products_finder_api.py",[84,117,152,179,206,223],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":103,"publishedAt":35},"01M6GJTE1GESGGF9K028Y7753E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fxurl\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[90,95,98],{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":96,"categoryName":97,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[86,104,21,105,106,22,23,107,108,109,110,111,112,27,28,113,55,114,115,116],"openclaw","cli","github","official","search","https","social-media","api","Media","twitter","social","via","post",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":134,"publishedAt":35},"01M6GJT8S1PXQ8WPXT1HSNBWH2","writing-plans","Write implementation plans: bite-sized tasks, paths, code.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwriting-plans\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[123,126,129,130,131],{"categoryNo":124,"categoryName":125,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":127,"categoryName":128,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":96,"categoryName":97,"taxonomyType":93,"taxonomyTypeDesc":94},{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},{"categoryNo":132,"categoryName":133,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000036","内容创作者",[135,136,137,138,21,139,22,140,23,141,142,143,144,145,146,147,148,149,150,151],"writing","writing plans","plans","design","review","workflow","documentation","tasks","development","code","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":161,"publishedAt":35},"01M6GJST0H5X7WHBJ3BZK0DVKH","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwhisper\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[158],{"categoryNo":159,"categoryName":160,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000016","图像与多媒体",[154,21,22,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178],"openai","speech","multimodal","Transformers","ASR","Audio","text","model","speech recognition","use","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":188,"publishedAt":35},"01M6GJSMRQ8EETZTYMG72P70EA","weights-and-biases","W&B: log ML experiments, sweeps, model registry, dashboards.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fweights-and-biases\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[185],{"categoryNo":186,"categoryName":187,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000013","分析与可视化",[189,21,190,191,23,192,193,194,195,196,197,169,198,199,200,201,202,203,204,205],"weights and biases","tensorflow","experiments","pytorch","visualization","registry","real-time","tuning","dashboards","experiment","log","time","Experiment Tracking","Model Registry","Hyperparameter Tuning","WandB","Real-Time Visualization",{"skillNo":207,"name":208,"nameZh":6,"description":209,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":210,"categories":211,"keywords":213,"publishedAt":35},"01M6GJS19KDPRY112JTR326S06","watchers","Poll RSS, JSON APIs, and GitHub with watermark dedup.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwatchers\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[212],{"categoryNo":96,"categoryName":97,"taxonomyType":93,"taxonomyTypeDesc":94},[208,21,214,106,22,215,216,217,218,219,220,27,28,221,222],"terminal","automation","http","monitoring","cron","json","rss","devops","with",{"skillNo":224,"name":225,"nameZh":6,"description":226,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":227,"categories":228,"keywords":231,"publishedAt":35},"01M6GJRHJD2A6Q830SWF9W48BC","serving-llms-vllm","vLLM: high-throughput LLM serving, OpenAI API, quantization.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fvllm\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[229,230],{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},[232,233,234,22,235,162,236,237,238,165,239,111,240,241,242,243,244,245,246,247],"llms","vLLM","serving llms vllm","research","openai api","tensor","Inference Serving","Production","llm serving","High Throughput","PagedAttention","Continuous Batching","Quantization","Tensor Parallelism","high-throughput","throughput"]