[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6E386D3VC0XSPBN06Z115Z0":3,"skill-same:01M6E386D3VC0XSPBN06Z115Z0":126},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":60,"repositoryHtmlUrl":61,"repositoryHomepageUrl":6,"ownerHtmlUrl":62,"ownerBlogUrl":6,"ownerDescription":63,"updatedAt":64,"install":65,"resources":78},"01M6E386D3VC0XSPBN06Z115Z0","serving-llms-vllm",null,"Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency\u002Fthroughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ\u002FAWQ\u002FFP8), and tensor parallelism.","luokai0\u002Fai-agent-skills-by-luo-kai","luokai0","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F266954973?v=4","01M6E16VNT42JB8B3X3254QWJ7","luo kai","01M6E16VTFVP6S5XJF1V1MPV90",14,"MIT","https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai\u002Fblob\u002Fmain\u002Fai-agent-skills\u002F09-data-and-ai (by Luo Kai)\u002F03-llm-engineering\u002Fvllm\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"vLLM","serving llms vllm","llms","use","Tensor Parallelism","Quantization","Continuous Batching","PagedAttention","High Throughput","latency","endpoints","models","api","Production","Transformers","Inference Serving","FP8","tensor","gpu","memory","2026-11-10 10:12:30",false,"---\nname: serving-llms-vllm\ndescription: Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency\u002Fthroughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ\u002FAWQ\u002FFP8), and tensor parallelism.\nversion: 1.0.0\nauthor: luo-kai\nlicense: MIT\ntags: [vLLM, Inference Serving, PagedAttention, Continuous Batching, High Throughput, Production, OpenAI API, Quantization, Tensor Parallelism]\ndependencies: [vllm, torch, transformers]\n---\n\n# vLLM - High-Performance LLM Serving\n\n## Quick start\n\nvLLM achieves 24x higher throughput than standard transformers through PagedAttention (block-based KV cache) and continuous batching (mixing prefill\u002Fdecode requests).\n\n**Installation**:\n```bash\npip install vllm\n```\n\n**Basic offline inference**:\n```python\nfrom vllm import LLM, SamplingParams\n\nllm = LLM(model=\"meta-llama\u002FLlama-3-8B-Instruct\")\nsampling = SamplingParams(temperature=0.7, max_tokens=256)\n\noutputs = llm.generate([\"Explain quantum computing\"], sampling)\nprint(outputs[0].outputs[0].text)\n```\n\n**OpenAI-compatible server**:\n```bash\nvllm serve meta-llama\u002FLlama-3-8B-Instruct\n\n# Query with OpenAI SDK\npython -c \"\nfrom openai import OpenAI\nclient = OpenAI(base_url='http:\u002F\u002Flocalhost:8000\u002Fv1', api_key='EMPTY')\nprint(client.chat.completions.create(\n    model='meta-llama\u002FLlama-3-8B-Instruct',\n    messages=[{'role': 'user', 'content': 'Hello!'}]\n).choices[0].message.content)\n\"\n```\n\n## Common workflows\n\n### Workflow 1: Production API deployment\n\nCopy this checklist and track progress:\n\n```\nDeployment Progress:\n- [ ] Step 1: Configure server settings\n- [ ] Step 2: Test with limited traffic\n- [ ] Step 3: Enable monitoring\n- [ ] Step 4: Deploy to production\n- [ ] Step 5: Verify performance metrics\n```\n\n**Step 1: Configure server settings**\n\nChoose configuration based on your model size:\n\n```bash\n# For 7B-13B models on single GPU\nvllm serve meta-llama\u002FLlama-3-8B-Instruct \\\n  --gpu-memory-utilization 0.9 \\\n  --max-model-len 8192 \\\n  --port 8000\n\n# For 30B-70B models with tensor parallelism\nvllm serve meta-llama\u002FLlama-2-70b-hf \\\n  --tensor-parallel-size 4 \\\n  --gpu-memory-utilization 0.9 \\\n  --quantization awq \\\n  --port 8000\n\n# For production with caching and metrics\nvllm serve meta-llama\u002FLlama-3-8B-Instruct \\\n  --gpu-memory-utilization 0.9 \\\n  --enable-prefix-caching \\\n  --enable-metrics \\\n  --metrics-port 9090 \\\n  --port 8000 \\\n  --host 0.0.0.0\n```\n\n**Step 2: Test with limited traffic**\n\nRun load test before production:\n\n```bash\n# Install load testing tool\npip install locust\n\n# Create test_load.py with sample requests\n# Run: locust -f test_load.py --host http:\u002F\u002Flocalhost:8000\n```\n\nVerify TTFT (time to first token) \u003C 500ms and throughput > 100 req\u002Fsec.\n\n**Step 3: Enable monitoring**\n\nvLLM exposes Prometheus metrics on port 9090:\n\n```bash\ncurl http:\u002F\u002Flocalhost:9090\u002Fmetrics | grep vllm\n```\n\nKey metrics to monitor:\n- `vllm:time_to_first_token_seconds` - Latency\n- `vllm:num_requests_running` - Active requests\n- `vllm:gpu_cache_usage_perc` - KV cache utilization\n\n**Step 4: Deploy to production**\n\nUse Docker for consistent deployment:\n\n```bash\n# Run vLLM in Docker\ndocker run --gpus all -p 8000:8000 \\\n  vllm\u002Fvllm-openai:latest \\\n  --model meta-llama\u002FLlama-3-8B-Instruct \\\n  --gpu-memory-utilization 0.9 \\\n  --enable-prefix-caching\n```\n\n**Step 5: Verify performance metrics**\n\nCheck that deployment meets targets:\n- TTFT \u003C 500ms (for short prompts)\n- Throughput > target req\u002Fsec\n- GPU utilization > 80%\n- No OOM errors in logs\n\n### Workflow 2: Offline batch inference\n\nFor processing large datasets without server overhead.\n\nCopy this checklist:\n\n```\nBatch Processing:\n- [ ] Step 1: Prepare input data\n- [ ] Step 2: Configure LLM engine\n- [ ] Step 3: Run batch inference\n- [ ] Step 4: Process results\n```\n\n**Step 1: Prepare input data**\n\n```python\n# Load prompts from file\nprompts = []\nwith open(\"prompts.txt\") as f:\n    prompts = [line.strip() for line in f]\n\nprint(f\"Loaded {len(prompts)} prompts\")\n```\n\n**Step 2: Configure LLM engine**\n\n```python\nfrom vllm import LLM, SamplingParams\n\nllm = LLM(\n    model=\"meta-llama\u002FLlama-3-8B-Instruct\",\n    tensor_parallel_size=2,  # Use 2 GPUs\n    gpu_memory_utilization=0.9,\n    max_model_len=4096\n)\n\nsampling = SamplingParams(\n    temperature=0.7,\n    top_p=0.95,\n    max_tokens=512,\n    stop=[\"\u003C\u002Fs>\", \"\\n\\n\"]\n)\n```\n\n**Step 3: Run batch inference**\n\nvLLM automatically batches requests for efficiency:\n\n```python\n# Process all prompts in one call\noutputs = llm.generate(prompts, sampling)\n\n# vLLM handles batching internally\n# No need to manually chunk prompts\n```\n\n**Step 4: Process results**\n\n```python\n# Extract generated text\nresults = []\nfor output in outputs:\n    prompt = output.prompt\n    generated = output.outputs[0].text\n    results.append({\n        \"prompt\": prompt,\n        \"generated\": generated,\n        \"tokens\": len(output.outputs[0].token_ids)\n    })\n\n# Save to file\nimport json\nwith open(\"results.jsonl\", \"w\") as f:\n    for result in results:\n        f.write(json.dumps(result) + \"\\n\")\n\nprint(f\"Processed {len(results)} prompts\")\n```\n\n### Workflow 3: Quantized model serving\n\nFit large models in limited GPU memory.\n\n```\nQuantization Setup:\n- [ ] Step 1: Choose quantization method\n- [ ] Step 2: Find or create quantized model\n- [ ] Step 3: Launch with quantization flag\n- [ ] Step 4: Verify accuracy\n```\n\n**Step 1: Choose quantization method**\n\n- **AWQ**: Best for 70B models, minimal accuracy loss\n- **GPTQ**: Wide model support, good compression\n- **FP8**: Fastest on H100 GPUs\n\n**Step 2: Find or create quantized model**\n\nUse pre-quantized models from HuggingFace:\n\n```bash\n# Search for AWQ models\n# Example: TheBloke\u002FLlama-2-70B-AWQ\n```\n\n**Step 3: Launch with quantization flag**\n\n```bash\n# Using pre-quantized model\nvllm serve TheBloke\u002FLlama-2-70B-AWQ \\\n  --quantization awq \\\n  --tensor-parallel-size 1 \\\n  --gpu-memory-utilization 0.95\n\n# Results: 70B model in ~40GB VRAM\n```\n\n**Step 4: Verify accuracy**\n\nTest outputs match expected quality:\n\n```python\n# Compare quantized vs non-quantized responses\n# Verify task-specific performance unchanged\n```\n\n## When to use vs alternatives\n\n**Use vLLM when:**\n- Deploying production LLM APIs (100+ req\u002Fsec)\n- Serving OpenAI-compatible endpoints\n- Limited GPU memory but need large models\n- Multi-user applications (chatbots, assistants)\n- Need low latency with high throughput\n\n**Use alternatives instead:**\n- **llama.cpp**: CPU\u002Fedge inference, single-user\n- **HuggingFace transformers**: Research, prototyping, one-off generation\n- **TensorRT-LLM**: NVIDIA-only, need absolute maximum performance\n- **Text-Generation-Inference**: Already in HuggingFace ecosystem\n\n## Common issues\n\n**Issue: Out of memory during model loading**\n\nReduce memory usage:\n```bash\nvllm serve MODEL \\\n  --gpu-memory-utilization 0.7 \\\n  --max-model-len 4096\n```\n\nOr use quantization:\n```bash\nvllm serve MODEL --quantization awq\n```\n\n**Issue: Slow first token (TTFT > 1 second)**\n\nEnable prefix caching for repeated prompts:\n```bash\nvllm serve MODEL --enable-prefix-caching\n```\n\nFor long prompts, enable chunked prefill:\n```bash\nvllm serve MODEL --enable-chunked-prefill\n```\n\n**Issue: Model not found error**\n\nUse `--trust-remote-code` for custom models:\n```bash\nvllm serve MODEL --trust-remote-code\n```\n\n**Issue: Low throughput (\u003C50 req\u002Fsec)**\n\nIncrease concurrent sequences:\n```bash\nvllm serve MODEL --max-num-seqs 512\n```\n\nCheck GPU utilization with `nvidia-smi` - should be >80%.\n\n**Issue: Inference slower than expected**\n\nVerify tensor parallelism uses power of 2 GPUs:\n```bash\nvllm serve MODEL --tensor-parallel-size 4  # Not 3\n```\n\nEnable speculative decoding for faster generation:\n```bash\nvllm serve MODEL --speculative-model DRAFT_MODEL\n```\n\n## Advanced topics\n\n**Server deployment patterns**: See [references\u002Fserver-deployment.md](references\u002Fserver-deployment.md) for Docker, Kubernetes, and load balancing configurations.\n\n**Performance optimization**: See [references\u002Foptimization.md](references\u002Foptimization.md) for PagedAttention tuning, continuous batching details, and benchmark results.\n\n**Quantization guide**: See [references\u002Fquantization.md](references\u002Fquantization.md) for AWQ\u002FGPTQ\u002FFP8 setup, model preparation, and accuracy comparisons.\n\n**Troubleshooting**: See [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for detailed error messages, debugging steps, and performance diagnostics.\n\n## Hardware requirements\n\n- **Small models (7B-13B)**: 1x A10 (24GB) or A100 (40GB)\n- **Medium models (30B-40B)**: 2x A100 (40GB) with tensor parallelism\n- **Large models (70B+)**: 4x A100 (40GB) or 2x A100 (80GB), use AWQ\u002FGPTQ\n\nSupported platforms: NVIDIA (primary), AMD ROCm, Intel GPUs, TPUs\n\n## Resources\n\n- Official docs: https:\u002F\u002Fdocs.vllm.ai\n- GitHub: https:\u002F\u002Fgithub.com\u002Fvllm-project\u002Fvllm\n- Paper: \"Efficient Memory Management for Large Language Model Serving with PagedAttention\" (SOSP 2023)\n- Community: https:\u002F\u002Fdiscuss.vllm.ai\n\n\n\n","# vLLM - High-Performance LLM Serving\n\n## Quick start\n\nvLLM achieves 24x higher throughput than standard transformers through PagedAttention (block-based KV cache) and continuous batching (mixing prefill\u002Fdecode requests).\n\n**Installation**:\n```bash\npip install vllm\n```\n\n**Basic offline inference**:\n```python\nfrom vllm import LLM, SamplingParams\n\nllm = LLM(model=\"meta-llama\u002FLlama-3-8B-Instruct\")\nsampling = SamplingParams(temperature=0.7, max_tokens=256)\n\noutputs = llm.generate([\"Explain quantum computing\"], sampling)\nprint(outputs[0].outputs[0].text)\n```\n\n**OpenAI-compatible server**:\n```bash\nvllm serve meta-llama\u002FLlama-3-8B-Instruct\n\n# Query with OpenAI SDK\npython -c \"\nfrom openai import OpenAI\nclient = OpenAI(base_url='http:\u002F\u002Flocalhost:8000\u002Fv1', api_key='EMPTY')\nprint(client.chat.completions.create(\n    model='meta-llama\u002FLlama-3-8B-Instruct',\n    messages=[{'role': 'user', 'content': 'Hello!'}]\n).choices[0].message.content)\n\"\n```\n\n## Common workflows\n\n### Workflow 1: Production API deployment\n\nCopy this checklist and track progress:\n\n```\nDeployment Progress:\n- [ ] Step 1: Configure server settings\n- [ ] Step 2: Test with limited traffic\n- [ ] Step 3: Enable monitoring\n- [ ] Step 4: Deploy to production\n- [ ] Step 5: Verify performance metrics\n```\n\n**Step 1: Configure server settings**\n\nChoose configuration based on your model size:\n\n```bash\n# For 7B-13B models on single GPU\nvllm serve meta-llama\u002FLlama-3-8B-Instruct \\\n  --gpu-memory-utilization 0.9 \\\n  --max-model-len 8192 \\\n  --port 8000\n\n# For 30B-70B models with tensor parallelism\nvllm serve meta-llama\u002FLlama-2-70b-hf \\\n  --tensor-parallel-size 4 \\\n  --gpu-memory-utilization 0.9 \\\n  --quantization awq \\\n  --port 8000\n\n# For production with caching and metrics\nvllm serve meta-llama\u002FLlama-3-8B-Instruct \\\n  --gpu-memory-utilization 0.9 \\\n  --enable-prefix-caching \\\n  --enable-metrics \\\n  --metrics-port 9090 \\\n  --port 8000 \\\n  --host 0.0.0.0\n```\n\n**Step 2: Test with limited traffic**\n\nRun load test before production:\n\n```bash\n# Install load testing tool\npip install locust\n\n# Create test_load.py with sample requests\n# Run: locust -f test_load.py --host http:\u002F\u002Flocalhost:8000\n```\n\nVerify TTFT (time to first token) \u003C 500ms and throughput > 100 req\u002Fsec.\n\n**Step 3: Enable monitoring**\n\nvLLM exposes Prometheus metrics on port 9090:\n\n```bash\ncurl http:\u002F\u002Flocalhost:9090\u002Fmetrics | grep vllm\n```\n\nKey metrics to monitor:\n- `vllm:time_to_first_token_seconds` - Latency\n- `vllm:num_requests_running` - Active requests\n- `vllm:gpu_cache_usage_perc` - KV cache utilization\n\n**Step 4: Deploy to production**\n\nUse Docker for consistent deployment:\n\n```bash\n# Run vLLM in Docker\ndocker run --gpus all -p 8000:8000 \\\n  vllm\u002Fvllm-openai:latest \\\n  --model meta-llama\u002FLlama-3-8B-Instruct \\\n  --gpu-memory-utilization 0.9 \\\n  --enable-prefix-caching\n```\n\n**Step 5: Verify performance metrics**\n\nCheck that deployment meets targets:\n- TTFT \u003C 500ms (for short prompts)\n- Throughput > target req\u002Fsec\n- GPU utilization > 80%\n- No OOM errors in logs\n\n### Workflow 2: Offline batch inference\n\nFor processing large datasets without server overhead.\n\nCopy this checklist:\n\n```\nBatch Processing:\n- [ ] Step 1: Prepare input data\n- [ ] Step 2: Configure LLM engine\n- [ ] Step 3: Run batch inference\n- [ ] Step 4: Process results\n```\n\n**Step 1: Prepare input data**\n\n```python\n# Load prompts from file\nprompts = []\nwith open(\"prompts.txt\") as f:\n    prompts = [line.strip() for line in f]\n\nprint(f\"Loaded {len(prompts)} prompts\")\n```\n\n**Step 2: Configure LLM engine**\n\n```python\nfrom vllm import LLM, SamplingParams\n\nllm = LLM(\n    model=\"meta-llama\u002FLlama-3-8B-Instruct\",\n    tensor_parallel_size=2,  # Use 2 GPUs\n    gpu_memory_utilization=0.9,\n    max_model_len=4096\n)\n\nsampling = SamplingParams(\n    temperature=0.7,\n    top_p=0.95,\n    max_tokens=512,\n    stop=[\"\u003C\u002Fs>\", \"\\n\\n\"]\n)\n```\n\n**Step 3: Run batch inference**\n\nvLLM automatically batches requests for efficiency:\n\n```python\n# Process all prompts in one call\noutputs = llm.generate(prompts, sampling)\n\n# vLLM handles batching internally\n# No need to manually chunk prompts\n```\n\n**Step 4: Process results**\n\n```python\n# Extract generated text\nresults = []\nfor output in outputs:\n    prompt = output.prompt\n    generated = output.outputs[0].text\n    results.append({\n        \"prompt\": prompt,\n        \"generated\": generated,\n        \"tokens\": len(output.outputs[0].token_ids)\n    })\n\n# Save to file\nimport json\nwith open(\"results.jsonl\", \"w\") as f:\n    for result in results:\n        f.write(json.dumps(result) + \"\\n\")\n\nprint(f\"Processed {len(results)} prompts\")\n```\n\n### Workflow 3: Quantized model serving\n\nFit large models in limited GPU memory.\n\n```\nQuantization Setup:\n- [ ] Step 1: Choose quantization method\n- [ ] Step 2: Find or create quantized model\n- [ ] Step 3: Launch with quantization flag\n- [ ] Step 4: Verify accuracy\n```\n\n**Step 1: Choose quantization method**\n\n- **AWQ**: Best for 70B models, minimal accuracy loss\n- **GPTQ**: Wide model support, good compression\n- **FP8**: Fastest on H100 GPUs\n\n**Step 2: Find or create quantized model**\n\nUse pre-quantized models from HuggingFace:\n\n```bash\n# Search for AWQ models\n# Example: TheBloke\u002FLlama-2-70B-AWQ\n```\n\n**Step 3: Launch with quantization flag**\n\n```bash\n# Using pre-quantized model\nvllm serve TheBloke\u002FLlama-2-70B-AWQ \\\n  --quantization awq \\\n  --tensor-parallel-size 1 \\\n  --gpu-memory-utilization 0.95\n\n# Results: 70B model in ~40GB VRAM\n```\n\n**Step 4: Verify accuracy**\n\nTest outputs match expected quality:\n\n```python\n# Compare quantized vs non-quantized responses\n# Verify task-specific performance unchanged\n```\n\n## When to use vs alternatives\n\n**Use vLLM when:**\n- Deploying production LLM APIs (100+ req\u002Fsec)\n- Serving OpenAI-compatible endpoints\n- Limited GPU memory but need large models\n- Multi-user applications (chatbots, assistants)\n- Need low latency with high throughput\n\n**Use alternatives instead:**\n- **llama.cpp**: CPU\u002Fedge inference, single-user\n- **HuggingFace transformers**: Research, prototyping, one-off generation\n- **TensorRT-LLM**: NVIDIA-only, need absolute maximum performance\n- **Text-Generation-Inference**: Already in HuggingFace ecosystem\n\n## Common issues\n\n**Issue: Out of memory during model loading**\n\nReduce memory usage:\n```bash\nvllm serve MODEL \\\n  --gpu-memory-utilization 0.7 \\\n  --max-model-len 4096\n```\n\nOr use quantization:\n```bash\nvllm serve MODEL --quantization awq\n```\n\n**Issue: Slow first token (TTFT > 1 second)**\n\nEnable prefix caching for repeated prompts:\n```bash\nvllm serve MODEL --enable-prefix-caching\n```\n\nFor long prompts, enable chunked prefill:\n```bash\nvllm serve MODEL --enable-chunked-prefill\n```\n\n**Issue: Model not found error**\n\nUse `--trust-remote-code` for custom models:\n```bash\nvllm serve MODEL --trust-remote-code\n```\n\n**Issue: Low throughput (\u003C50 req\u002Fsec)**\n\nIncrease concurrent sequences:\n```bash\nvllm serve MODEL --max-num-seqs 512\n```\n\nCheck GPU utilization with `nvidia-smi` - should be >80%.\n\n**Issue: Inference slower than expected**\n\nVerify tensor parallelism uses power of 2 GPUs:\n```bash\nvllm serve MODEL --tensor-parallel-size 4  # Not 3\n```\n\nEnable speculative decoding for faster generation:\n```bash\nvllm serve MODEL --speculative-model DRAFT_MODEL\n```\n\n## Advanced topics\n\n**Server deployment patterns**: See [references\u002Fserver-deployment.md](references\u002Fserver-deployment.md) for Docker, Kubernetes, and load balancing configurations.\n\n**Performance optimization**: See [references\u002Foptimization.md](references\u002Foptimization.md) for PagedAttention tuning, continuous batching details, and benchmark results.\n\n**Quantization guide**: See [references\u002Fquantization.md](references\u002Fquantization.md) for AWQ\u002FGPTQ\u002FFP8 setup, model preparation, and accuracy comparisons.\n\n**Troubleshooting**: See [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for detailed error messages, debugging steps, and performance diagnostics.\n\n## Hardware requirements\n\n- **Small models (7B-13B)**: 1x A10 (24GB) or A100 (40GB)\n- **Medium models (30B-40B)**: 2x A100 (40GB) with tensor parallelism\n- **Large models (70B+)**: 4x A100 (40GB) or 2x A100 (80GB), use AWQ\u002FGPTQ\n\nSupported platforms: NVIDIA (primary), AMD ROCm, Intel GPUs, TPUs\n\n## Resources\n\n- Official docs: https:\u002F\u002Fdocs.vllm.ai\n- GitHub: https:\u002F\u002Fgithub.com\u002Fvllm-project\u002Fvllm\n- Paper: \"Efficient Memory Management for Large Language Model Serving with PagedAttention\" (SOSP 2023)\n- Community: https:\u002F\u002Fdiscuss.vllm.ai\n\n\n\n",{"name":5,"tags":49,"author":51,"license":15,"version":52,"description":7,"dependencies":53},[24,39,31,30,32,37,50,29,28],"OpenAI API","luo-kai","1.0.0",[54,55,56],"vllm","torch","transformers","main","4d2fb89cdfb75f3f6fd3c6c5ec9ad90ea129eb3c","ai-agent-skills\u002F09-data-and-ai (by Luo Kai)\u002F03-llm-engineering\u002Fvllm",2,"https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai","https:\u002F\u002Fgithub.com\u002Fluokai0","a solo builder.","2026-05-06 04:29:04",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add luokai0\u002Fai-agent-skills-by-luo-kai --skill serving-llms-vllm",{"tool":71,"command":72},"bunx","bunx skills add luokai0\u002Fai-agent-skills-by-luo-kai --skill serving-llms-vllm",{"tool":74,"command":75},"pnpm","pnpm dlx skills add luokai0\u002Fai-agent-skills-by-luo-kai --skill serving-llms-vllm","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai\u002Fblob\u002Fmain\u002Fai-agent-skills\u002F09-data-and-ai (by Luo Kai)\u002F03-llm-engineering\u002Fvllm\u002FSKILL.md",true,[79,85,89,95,99,103,107,111,115,119,123],{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"examples.py","SCRIPT","脚本",5672,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fresearch-lookup\u002Fexamples.py",{"path":86,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":87,"sourceHtmlUrl":88},"lookup.py",5957,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fresearch-lookup\u002Flookup.py",{"path":90,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":93,"sourceHtmlUrl":94},"README.md","REFERENCE","参考文档",5606,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fresearch-lookup\u002FREADME.md",{"path":96,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":97,"sourceHtmlUrl":98},"references\u002Foptimization.md",5769,"https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai\u002Fblob\u002Fmain\u002Fai-agent-skills\u002F09-data-and-ai (by Luo Kai)\u002F03-llm-engineering\u002Fvllm\u002Freferences\u002Foptimization.md",{"path":100,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":101,"sourceHtmlUrl":102},"references\u002Fquantization.md",6746,"https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai\u002Fblob\u002Fmain\u002Fai-agent-skills\u002F09-data-and-ai (by Luo Kai)\u002F03-llm-engineering\u002Fvllm\u002Freferences\u002Fquantization.md",{"path":104,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":105,"sourceHtmlUrl":106},"references\u002Fserver-deployment.md",5252,"https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai\u002Fblob\u002Fmain\u002Fai-agent-skills\u002F09-data-and-ai (by Luo Kai)\u002F03-llm-engineering\u002Fvllm\u002Freferences\u002Fserver-deployment.md",{"path":108,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":109,"sourceHtmlUrl":110},"references\u002Ftroubleshooting.md",9037,"https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai\u002Fblob\u002Fmain\u002Fai-agent-skills\u002F09-data-and-ai (by Luo Kai)\u002F03-llm-engineering\u002Fvllm\u002Freferences\u002Ftroubleshooting.md",{"path":112,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":113,"sourceHtmlUrl":114},"research_lookup.py",22642,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fresearch-lookup\u002Fresearch_lookup.py",{"path":116,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":117,"sourceHtmlUrl":118},"scripts\u002Fgenerate_schematic_ai.py",32647,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fresearch-lookup\u002Fscripts\u002Fgenerate_schematic_ai.py",{"path":120,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":121,"sourceHtmlUrl":122},"scripts\u002Fgenerate_schematic.py",5146,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fresearch-lookup\u002Fscripts\u002Fgenerate_schematic.py",{"path":124,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":113,"sourceHtmlUrl":125},"scripts\u002Fresearch_lookup.py","https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fresearch-lookup\u002Fscripts\u002Fresearch_lookup.py",[127,154,171,199,231,264],{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":44},"01M6F2SKTE208174C7S7JJCZC7","write-contracts","Generates secure Aptos Move V2 smart contracts with Object model, Digital Asset integration, security patterns, and storage type guidance. Includes comprehensive storage decision framework for optimal data structure selection. Triggers on: 'write contract', 'create NFT collection', 'build marketplace', 'implement minting', 'generate Move module', 'create token contract', 'build DAO', 'implement staking'. Ask storage questions when: 'store', 'track', 'registry', 'mapping', 'list', 'collection'.","https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai\u002Fblob\u002Fmain\u002Fai-agent-skills\u002F22-clawhub-skills\u002Fwrite-contracts\u002FSKILL.md",[],[134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153],"write","contracts","write contracts","storage","secure","create","generate","collection","model","decision","ask","smart-contracts","selection","objects","structure","nft","token","aptos","critical","move",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":160,"publishedAt":44},"01M6F2RFXJ6T9MKW0A7N7GM45B","web-search","通用网络搜索技能，支持多引擎搜索（百度、必应、DuckDuckGo），无需API密钥即可获取实时信息","https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai\u002Fblob\u002Fmain\u002Fai-agent-skills\u002F22-clawhub-skills\u002Fweb-search-ex-skill\u002FSKILL.md",[],[161,162,163,164,165,166,167,168,169,170],"web","search","web search","搜索","baidu","bing","duckduckgo","百度","多引擎","internet",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":180,"publishedAt":44},"01M6F2K968G1FZEZFPW2E6B222","solo-build","Execute implementation plan tasks with TDD workflow, auto-commit, and phase gates. Use when user says \"build it\", \"start building\", \"execute plan\", \"implement tasks\", \"ship it\", or references a track ID. Do NOT use for planning (use \u002Fplan) or scaffolding (use \u002Fscaffold).","https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai\u002Fblob\u002Fmain\u002Fai-agent-skills\u002F22-clawhub-skills\u002Fsolo-build\u002FSKILL.md",[177],{"categoryNo":178,"categoryName":179,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[181,182,183,184,185,186,187,188,162,189,190,191,134,192,193,194,195,196,197,198],"build","solo","solo build","MCP","workflow","commit","tasks","code","Bash","plan","read","auto","references","context7","query","scaffolding","ship it","project",{"skillNo":200,"name":201,"nameZh":6,"description":202,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":203,"categories":204,"keywords":211,"publishedAt":44},"01M6F2GKN39SGHSPWYB3662YC8","react-email","Use when building HTML email templates with React components, adding a visual email editor to an application using the React Email visual editor, rendering emails to HTML, or sending emails with Resend. Covers welcome emails, password resets, notifications, order confirmations, newsletters, transactional emails, and the embeddable email editor component.","https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai\u002Fblob\u002Fmain\u002Fai-agent-skills\u002F22-clawhub-skills\u002Freact-email-skills\u002FSKILL.md",[205,208],{"categoryNo":206,"categoryName":207,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000005","邮件与沟通",{"categoryNo":209,"categoryName":210,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[212,213,214,215,216,217,218,219,220,221,222,223,224,27,225,226,227,228,229,230],"react","email","react email","github","editor","components","react components","component","welcome","https","notifications","password","node","html","resend","visual","emails","rendering","with",{"skillNo":232,"name":233,"nameZh":6,"description":234,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":235,"categories":236,"keywords":247,"publishedAt":44},"01M6F2FBVGVDFSG8SSFJGXA40C","APITester Agent-Driven API Testing","Test API endpoints and document responses. Define tests in plain English, run them, get formatted results. Agent-driven Postman alternative.","https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai\u002Fblob\u002Fmain\u002Fai-agent-skills\u002F22-clawhub-skills\u002Fopenclaw-api-tester\u002FSKILL.md",[237,240,241,242],{"categoryNo":238,"categoryName":239,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":178,"categoryName":179,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":243,"categoryName":244,"taxonomyType":245,"taxonomyTypeDesc":246},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[248,36,249,250,251,252,253,254,255,256,257,34,258,259,260,261,262,263],"testing","api testing","driven","APITester Agent Driven API Testing","test","run","postman","results","plain english","tester","document","get","define","tests","english","api-tester",{"skillNo":265,"name":266,"nameZh":6,"description":267,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":268,"categories":269,"keywords":270,"publishedAt":44},"01M6F273Y3NGAPVJZ608BC0G9G","hubspot-implementation-plan","Generate a phased implementation plan from a HubSpot audit report. Creates prioritized, sequenced cleanup processes with effort estimates, dependencies, and automation feasibility. Use after running \u002Fhubspot-audit.","https:\u002F\u002Fgithub.com\u002Fluokai0\u002Fai-agent-skills-by-luo-kai\u002Fblob\u002Fmain\u002Fai-agent-skills\u002F22-clawhub-skills\u002Fhubspot-implementation-plan\u002FSKILL.md",[],[190,271,272,273,274,275,276,140,277,278,279,280,281,27,282,283,230,284],"implementation","hubspot","hubspot implementation plan","automation","feasibility","cleanup","planning","report","audit","audit report","phased implementation","dependencies","processes","hubspot audit"]