[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71F7Q3R8M1VDNS1WTMKMSQJ":3,"skill-same:01M71F7Q3R8M1VDNS1WTMKMSQJ":102},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":64,"commitSha":65,"skillDirectory":66,"forksCount":13,"repositoryHtmlUrl":67,"repositoryHomepageUrl":6,"ownerHtmlUrl":68,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":69,"install":70,"resources":83},"01M71F7Q3R8M1VDNS1WTMKMSQJ","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.","gjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6","gjbvsjjvgm-sketch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F278511911?v=4","01M71F3JXKZQ70H2KCHHTXKZDA","01M71F3JY8A79Z3NZBW08TF4JD",0,"MIT","https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002F.hermes\u002Fskills\u002Fmlops\u002Finference\u002Fvllm\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"llms","serving","vLLM","serving llms vllm","when","batching","orchestra","openai-compatible","throughput","GPTQ","AWQ","latency","use","api","Transformers","Inference Serving","FP8","openai api","openai","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: 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\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,"author":48,"license":14,"version":49,"metadata":50,"description":7,"dependencies":60},"Orchestra Research","1.0.0",{"hermes":51},{"tags":52},[25,38,53,54,55,56,57,58,59],"PagedAttention","Continuous Batching","High Throughput","Production","OpenAI API","Quantization","Tensor Parallelism",[61,62,63],"vllm","torch","transformers","main","93bbc269671fbb340afa15b36a8766f15dc30df2",".hermes\u002Fskills\u002Fmlops\u002Finference\u002Fvllm","https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6","https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch","2026-04-27 02:51:28",{"source":8,"skillName":5,"commands":71,"prompt":81,"zipAvailable":82},[72,75,78],{"tool":73,"command":74},"npx","npx skills add gjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6 --skill serving-llms-vllm",{"tool":76,"command":77},"bunx","bunx skills add gjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6 --skill serving-llms-vllm",{"tool":79,"command":80},"pnpm","pnpm dlx skills add gjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6 --skill serving-llms-vllm","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002F.hermes\u002Fskills\u002Fmlops\u002Finference\u002Fvllm\u002FSKILL.md",true,[84,90,94,98],{"path":85,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Foptimization.md","REFERENCE","参考文档",5769,"https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002F.hermes\u002Fskills\u002Fmlops\u002Finference\u002Fvllm\u002Freferences\u002Foptimization.md",{"path":91,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fquantization.md",6746,"https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002F.hermes\u002Fskills\u002Fmlops\u002Finference\u002Fvllm\u002Freferences\u002Fquantization.md",{"path":95,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fserver-deployment.md",5252,"https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002F.hermes\u002Fskills\u002Fmlops\u002Finference\u002Fvllm\u002Freferences\u002Fserver-deployment.md",{"path":99,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Ftroubleshooting.md",9037,"https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002F.hermes\u002Fskills\u002Fmlops\u002Finference\u002Fvllm\u002Freferences\u002Ftroubleshooting.md",[103,143,171,186,205,226],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":123,"publishedAt":43},"01M71G6TJ2RAQ1J0PV3K6D9GQA","writing-plans","Use when you have a spec or requirements for a multi-step task. Creates comprehensive implementation plans with bite-sized tasks, exact file paths, and complete code examples.","https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002Fhermes_sovereign_data\u002Fskills\u002Fsoftware-development\u002Fwriting-plans\u002FSKILL.md",[109,112,115,120],{"categoryNo":110,"categoryName":111,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":113,"categoryName":114,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":116,"categoryName":117,"taxonomyType":118,"taxonomyTypeDesc":119},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":121,"categoryName":122,"taxonomyType":118,"taxonomyTypeDesc":119},"01JBSEEDCAT000000000000036","内容创作者",[124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,27],"writing","writing plans","plans","design","review","workflow","documentation","tasks","development","code","planning","code-review","subagent","superpowers","paths","test-driven-development","you","for","test-driven",{"skillNo":144,"name":139,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":156,"publishedAt":43},"01M71G6R81013R3T7W5VP56GCB","Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR cycle with test-first approach.","https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002Fhermes_sovereign_data\u002Fskills\u002Fsoftware-development\u002Ftest-driven-development\u002FSKILL.md",[148,151,154,155],{"categoryNo":149,"categoryName":150,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":152,"categoryName":153,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":113,"categoryName":114,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":121,"categoryName":122,"taxonomyType":118,"taxonomyTypeDesc":119},[157,158,132,159,160,124,161,133,162,136,137,163,164,165,166,167,168,169,170,27],"test","test driven development","driven","testing","debugging","refactor","red-green-refactor","cycle","green","systematic","bugfix","implementing","systematic-debugging","test-first",{"skillNo":172,"name":169,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":177,"publishedAt":43},"01M71G6N0Y546JZEDF25E2PMCE","Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.","https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002Fhermes_sovereign_data\u002Fskills\u002Fsoftware-development\u002Fsystematic-debugging\u002FSKILL.md",[176],{"categoryNo":152,"categoryName":153,"taxonomyType":20,"taxonomyTypeDesc":21},[178,161,166,124,157,132,136,35,137,179,180,181,126,182,139,183,142,184,185,27],"systematic debugging","bug","root-cause","problem-solving","problem","fixes","phase","root cause",{"skillNo":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":190,"categories":191,"keywords":198,"publishedAt":43},"01M71G6J0DXEGY48GH4KVW2SJH","subagent-driven-development","Use when executing implementation plans with independent tasks. Dispatches fresh delegate_task per task with two-stage review (spec compliance then code quality).","https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002Fhermes_sovereign_data\u002Fskills\u002Fsoftware-development\u002Fsubagent-driven-development\u002FSKILL.md",[192,193,194,195],{"categoryNo":113,"categoryName":114,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":116,"categoryName":117,"taxonomyType":118,"taxonomyTypeDesc":119},{"categoryNo":121,"categoryName":122,"taxonomyType":118,"taxonomyTypeDesc":119},{"categoryNo":196,"categoryName":197,"taxonomyType":118,"taxonomyTypeDesc":119},"01JBSEEDCAT000000000000037","律师与法务",[132,199,136,159,124,128,129,200,131,133,201,135,202,203,137,126,204,139,142,27],"subagent driven development","code quality","delegation","parallel","delegate","fresh",{"skillNo":206,"name":207,"nameZh":6,"description":208,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":209,"categories":210,"keywords":213,"publishedAt":43},"01M71G6EFFBQX6634E6XHB09Y1","requesting-code-review","Pre-commit verification pipeline — static security scan, baseline-aware quality gates, independent reviewer subagent, and auto-fix loop. Use after code changes and before committing, pushing, or opening a PR.","https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002Fhermes_sovereign_data\u002Fskills\u002Fsoftware-development\u002Frequesting-code-review\u002FSKILL.md",[211,212],{"categoryNo":149,"categoryName":150,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":116,"categoryName":117,"taxonomyType":118,"taxonomyTypeDesc":119},[214,128,133,215,124,216,135,217,218,219,220,136,221,222,223,137,139,224,225,142],"code review","requesting code review","commit","verification","security scan","pipeline","loop","reviewer","fix","auto","static","auto-fix",{"skillNo":227,"name":228,"nameZh":6,"description":229,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":230,"categories":231,"keywords":232,"publishedAt":43},"01M71G6CM8ANSWVFXCN9AAD58Y","plan","Plan mode for Hermes — inspect context, write a markdown plan into the active workspace's `.hermes\u002Fplans\u002F` directory, and do not execute the work.","https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002Fhermes_sovereign_data\u002Fskills\u002Fsoftware-development\u002Fplan\u002FSKILL.md",[],[228,124,233,129,132,134,234,136,235,236,237,238,239,240,126,241,242,243,141,244],"directory","markdown","workspace","work","write","implementation","do","active","plan mode","inspect","mode","plan-mode"]