[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71NJ1FPNAKJB53BXWAS4JTY":3,"skill-same:01M71NJ1FPNAKJB53BXWAS4JTY":105},{"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":65,"commitSha":66,"skillDirectory":67,"forksCount":68,"repositoryHtmlUrl":69,"repositoryHomepageUrl":6,"ownerHtmlUrl":70,"ownerBlogUrl":6,"ownerDescription":71,"updatedAt":72,"install":73,"resources":86},"01M71NJ1FPNAKJB53BXWAS4JTY","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.","q2805187159\u002FAnvil","q2805187159","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F105276843?v=4","01M71KF4TN999VNJX9FY9QT06A","铁甲勇士宋小宝","01M71KF4V97XXQ7AGES97R4Q9F",3,"MIT","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fmlops\u002Finference\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","serving llms vllm","llms","use","batching","FP8","GPTQ","orchestra","latency","AWQ","openai-compatible","throughput","openai api","openai","Transformers","Inference Serving","api","when","memory","2026-11-10 10:56:23",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: Orchestra Research\nlicense: MIT\ndependencies: [vllm, torch, transformers]\nmetadata:\n  hermes:\n    tags: [vLLM, Inference Serving, PagedAttention, Continuous Batching, High Throughput, Production, OpenAI API, Quantization, Tensor Parallelism]\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","# 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",{"name":5,"author":49,"license":15,"version":50,"metadata":51,"description":7,"dependencies":61},"Orchestra Research","1.0.0",{"hermes":52},{"tags":53},[24,40,54,55,56,57,58,59,60],"PagedAttention","Continuous Batching","High Throughput","Production","OpenAI API","Quantization","Tensor Parallelism",[62,63,64],"vllm","torch","transformers","main","6ffadc67c9777282fa1f9330ec12ac8778064409","skills\u002Fmlops\u002Finference\u002Fvllm",0,"https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil","https:\u002F\u002Fgithub.com\u002Fq2805187159","Independent Researcher\r\n\r\nEmail: q2805187159@gmail.com\r\n\r\nGithub: q2805187159\r\n\r\nResearch Interests:\r\n- LLM Agents\r\n- Tool Routing\r\n- RAG","2026-06-24 18:31:41",{"source":8,"skillName":5,"commands":74,"prompt":84,"zipAvailable":85},[75,78,81],{"tool":76,"command":77},"npx","npx skills add q2805187159\u002FAnvil --skill serving-llms-vllm",{"tool":79,"command":80},"bunx","bunx skills add q2805187159\u002FAnvil --skill serving-llms-vllm",{"tool":82,"command":83},"pnpm","pnpm dlx skills add q2805187159\u002FAnvil --skill serving-llms-vllm","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fmlops\u002Finference\u002Fvllm\u002FSKILL.md",true,[87,93,97,101],{"path":88,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Foptimization.md","REFERENCE","参考文档",5769,"https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fmlops\u002Finference\u002Fvllm\u002Freferences\u002Foptimization.md",{"path":94,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fquantization.md",6746,"https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fmlops\u002Finference\u002Fvllm\u002Freferences\u002Fquantization.md",{"path":98,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002Fserver-deployment.md",5252,"https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fmlops\u002Finference\u002Fvllm\u002Freferences\u002Fserver-deployment.md",{"path":102,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":103,"sourceHtmlUrl":104},"references\u002Ftroubleshooting.md",9037,"https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fmlops\u002Finference\u002Fvllm\u002Freferences\u002Ftroubleshooting.md",[106,138,169,176,202,225],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":110,"licenseFileUrl":111,"sourceHtmlUrl":112,"categories":113,"keywords":120,"publishedAt":44},"01M71NPWVVMB1AZ8XGKNJFT0YP","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[114,117],{"categoryNo":115,"categoryName":116,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":118,"categoryName":119,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137],"webapp","testing","webapp testing","for","applications","local","frontend","debugging","toolkit","logs","browser","with","playwright","web","behavior","ui","screenshots",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":152,"publishedAt":44},"01M71NPTQ96H4XSZVZT422BNRB","web-design-guidelines","Review UI code for Web Interface Guidelines compliance. Use when asked to \"review my UI\", \"check accessibility\", \"audit design\", \"review UX\", or \"check my site against best practices\".","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fweb-design-guidelines\u002FSKILL.md",[144,147],{"categoryNo":145,"categoryName":146,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":148,"categoryName":149,"taxonomyType":150,"taxonomyTypeDesc":151},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[153,154,134,155,156,124,157,158,159,28,42,160,161,162,163,164,165,166,167,168],"guidelines","design","web design guidelines","web design","vercel","interface","web interface guidelines","best practices","file","code","review","check","compliance","audit","ux","accessibility",{"skillNo":170,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":175,"publishedAt":44},"01M71NPS2D31Y2BGFYA9DB7CE4","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fweb-design-guidelines copy\u002FSKILL.md",[173,174],{"categoryNo":145,"categoryName":146,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":148,"categoryName":149,"taxonomyType":150,"taxonomyTypeDesc":151},[153,154,134,155,156,124,157,158,159,28,42,160,161,162,163,164,165,166,167,168],{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":188,"publishedAt":44},"01M71NPQ9DRT54QSQJ0BHBM3VG","video-generation","Use this skill when the user requests to generate, create, or imagine videos. Supports structured prompts and reference image for guided generation.","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-generation\u002FSKILL.md",[182,185],{"categoryNo":183,"categoryName":184,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":186,"categoryName":187,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[189,190,191,124,28,42,192,193,194,195,196,197,198,199,200,201],"Video","video generation","generation","image","create","imagine","requests","generate","videos","reference","prompts","user","structured",{"skillNo":203,"name":204,"nameZh":6,"description":205,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":206,"categories":207,"keywords":209,"publishedAt":44},"01M71NPN57CT154SWXAS52475X","youtube-downloader","Download YouTube videos with customizable quality and format options. Use this skill when the user asks to download, save, or grab YouTube videos. Supports various quality settings (best, 1080p, 720p, 480p, 360p), multiple formats (mp4, webm, mkv), and audio-only downloads as MP3.","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-downloader\u002FSKILL.md",[208],{"categoryNo":183,"categoryName":184,"taxonomyType":21,"taxonomyTypeDesc":22},[210,211,212,213,214,215,216,28,42,217,132,218,219,220,221,222,197,223,200,224],"youtube","youtube downloader","mp4","as","downloads","Audio","only","mp3","options","quality","format","settings","grab","formats","download",{"skillNo":226,"name":227,"nameZh":6,"description":228,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":229,"categories":230,"keywords":231,"publishedAt":44},"01M71NPKD95YB8N3J6J78QGFFW","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fq2805187159\u002FAnvil\u002Fblob\u002Fmain\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[232,233,234,235,236,237,238,28,239,42,240,241,242,243,244,245],"verification","verification before completion","running","evidence","complete","prs","claim","assertions","committing","output","claims","work","about","commands"]