[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7D2YJFPEXVDFBVE99R970QM":3,"skill-same:01M7D2YJFPEXVDFBVE99R970QM":73},{"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":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":13,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":44,"install":45,"resources":58},"01M7D2YJFPEXVDFBVE99R970QM","tensorrt-llm",null,"Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100\u002FH100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8\u002FINT4), in-flight batching, and multi-GPU scaling.","beyondai\u002Fsandbox","beyondai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F2845958?v=4","01M7D24SBNM47BJGJ9J2HB13BP","01M7D24SCDC9DYE005XH6R553S",0,"MIT","https:\u002F\u002Fgithub.com\u002Fbeyondai\u002Fsandbox\u002Fblob\u002Fmain\u002Flabs\u002F.codex\u002Fskills\u002Ftensorrt-llm\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: tensorrt-llm\ndescription: Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100\u002FH100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8\u002FINT4), in-flight batching, and multi-GPU scaling.\nversion: 1.0.0\nauthor: Orchestra Research\nlicense: MIT\ntags: [Inference Serving, TensorRT-LLM, NVIDIA, Inference Optimization, High Throughput, Low Latency, Production, FP8, INT4, In-Flight Batching, Multi-GPU]\ndependencies: [tensorrt-llm, torch]\n---\n\n# TensorRT-LLM\n\nNVIDIA's open-source library for optimizing LLM inference with state-of-the-art performance on NVIDIA GPUs.\n\n## When to use TensorRT-LLM\n\n**Use TensorRT-LLM when:**\n- Deploying on NVIDIA GPUs (A100, H100, GB200)\n- Need maximum throughput (24,000+ tokens\u002Fsec on Llama 3)\n- Require low latency for real-time applications\n- Working with quantized models (FP8, INT4, FP4)\n- Scaling across multiple GPUs or nodes\n\n**Use vLLM instead when:**\n- Need simpler setup and Python-first API\n- Want PagedAttention without TensorRT compilation\n- Working with AMD GPUs or non-NVIDIA hardware\n\n**Use llama.cpp instead when:**\n- Deploying on CPU or Apple Silicon\n- Need edge deployment without NVIDIA GPUs\n- Want simpler GGUF quantization format\n\n## Quick start\n\n### Installation\n\n```bash\n# Docker (recommended)\ndocker pull nvidia\u002Ftensorrt_llm:latest\n\n# pip install\npip install tensorrt_llm==1.2.0rc3\n\n# Requires CUDA 13.0.0, TensorRT 10.13.2, Python 3.10-3.12\n```\n\n### Basic inference\n\n```python\nfrom tensorrt_llm import LLM, SamplingParams\n\n# Initialize model\nllm = LLM(model=\"meta-llama\u002FMeta-Llama-3-8B\")\n\n# Configure sampling\nsampling_params = SamplingParams(\n    max_tokens=100,\n    temperature=0.7,\n    top_p=0.9\n)\n\n# Generate\nprompts = [\"Explain quantum computing\"]\noutputs = llm.generate(prompts, sampling_params)\n\nfor output in outputs:\n    print(output.text)\n```\n\n### Serving with trtllm-serve\n\n```bash\n# Start server (automatic model download and compilation)\ntrtllm-serve meta-llama\u002FMeta-Llama-3-8B \\\n    --tp_size 4 \\              # Tensor parallelism (4 GPUs)\n    --max_batch_size 256 \\\n    --max_num_tokens 4096\n\n# Client request\ncurl -X POST http:\u002F\u002Flocalhost:8000\u002Fv1\u002Fchat\u002Fcompletions \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"model\": \"meta-llama\u002FMeta-Llama-3-8B\",\n    \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}],\n    \"temperature\": 0.7,\n    \"max_tokens\": 100\n  }'\n```\n\n## Key features\n\n### Performance optimizations\n- **In-flight batching**: Dynamic batching during generation\n- **Paged KV cache**: Efficient memory management\n- **Flash Attention**: Optimized attention kernels\n- **Quantization**: FP8, INT4, FP4 for 2-4× faster inference\n- **CUDA graphs**: Reduced kernel launch overhead\n\n### Parallelism\n- **Tensor parallelism (TP)**: Split model across GPUs\n- **Pipeline parallelism (PP)**: Layer-wise distribution\n- **Expert parallelism**: For Mixture-of-Experts models\n- **Multi-node**: Scale beyond single machine\n\n### Advanced features\n- **Speculative decoding**: Faster generation with draft models\n- **LoRA serving**: Efficient multi-adapter deployment\n- **Disaggregated serving**: Separate prefill and generation\n\n## Common patterns\n\n### Quantized model (FP8)\n\n```python\nfrom tensorrt_llm import LLM\n\n# Load FP8 quantized model (2× faster, 50% memory)\nllm = LLM(\n    model=\"meta-llama\u002FMeta-Llama-3-70B\",\n    dtype=\"fp8\",\n    max_num_tokens=8192\n)\n\n# Inference same as before\noutputs = llm.generate([\"Summarize this article...\"])\n```\n\n### Multi-GPU deployment\n\n```python\n# Tensor parallelism across 8 GPUs\nllm = LLM(\n    model=\"meta-llama\u002FMeta-Llama-3-405B\",\n    tensor_parallel_size=8,\n    dtype=\"fp8\"\n)\n```\n\n### Batch inference\n\n```python\n# Process 100 prompts efficiently\nprompts = [f\"Question {i}: ...\" for i in range(100)]\n\noutputs = llm.generate(\n    prompts,\n    sampling_params=SamplingParams(max_tokens=200)\n)\n\n# Automatic in-flight batching for maximum throughput\n```\n\n## Performance benchmarks\n\n**Meta Llama 3-8B** (H100 GPU):\n- Throughput: 24,000 tokens\u002Fsec\n- Latency: ~10ms per token\n- vs PyTorch: **100× faster**\n\n**Llama 3-70B** (8× A100 80GB):\n- FP8 quantization: 2× faster than FP16\n- Memory: 50% reduction with FP8\n\n## Supported models\n\n- **LLaMA family**: Llama 2, Llama 3, CodeLlama\n- **GPT family**: GPT-2, GPT-J, GPT-NeoX\n- **Qwen**: Qwen, Qwen2, QwQ\n- **DeepSeek**: DeepSeek-V2, DeepSeek-V3\n- **Mixtral**: Mixtral-8x7B, Mixtral-8x22B\n- **Vision**: LLaVA, Phi-3-vision\n- **100+ models** on HuggingFace\n\n## References\n\n- **[Optimization Guide](references\u002Foptimization.md)** - Quantization, batching, KV cache tuning\n- **[Multi-GPU Setup](references\u002Fmulti-gpu.md)** - Tensor\u002Fpipeline parallelism, multi-node\n- **[Serving Guide](references\u002Fserving.md)** - Production deployment, monitoring, autoscaling\n\n## Resources\n\n- **Docs**: https:\u002F\u002Fnvidia.github.io\u002FTensorRT-LLM\u002F\n- **GitHub**: https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FTensorRT-LLM\n- **Models**: https:\u002F\u002Fhuggingface.co\u002Fmodels?library=tensorrt_llm\n\n\n","# TensorRT-LLM\n\nNVIDIA's open-source library for optimizing LLM inference with state-of-the-art performance on NVIDIA GPUs.\n\n## When to use TensorRT-LLM\n\n**Use TensorRT-LLM when:**\n- Deploying on NVIDIA GPUs (A100, H100, GB200)\n- Need maximum throughput (24,000+ tokens\u002Fsec on Llama 3)\n- Require low latency for real-time applications\n- Working with quantized models (FP8, INT4, FP4)\n- Scaling across multiple GPUs or nodes\n\n**Use vLLM instead when:**\n- Need simpler setup and Python-first API\n- Want PagedAttention without TensorRT compilation\n- Working with AMD GPUs or non-NVIDIA hardware\n\n**Use llama.cpp instead when:**\n- Deploying on CPU or Apple Silicon\n- Need edge deployment without NVIDIA GPUs\n- Want simpler GGUF quantization format\n\n## Quick start\n\n### Installation\n\n```bash\n# Docker (recommended)\ndocker pull nvidia\u002Ftensorrt_llm:latest\n\n# pip install\npip install tensorrt_llm==1.2.0rc3\n\n# Requires CUDA 13.0.0, TensorRT 10.13.2, Python 3.10-3.12\n```\n\n### Basic inference\n\n```python\nfrom tensorrt_llm import LLM, SamplingParams\n\n# Initialize model\nllm = LLM(model=\"meta-llama\u002FMeta-Llama-3-8B\")\n\n# Configure sampling\nsampling_params = SamplingParams(\n    max_tokens=100,\n    temperature=0.7,\n    top_p=0.9\n)\n\n# Generate\nprompts = [\"Explain quantum computing\"]\noutputs = llm.generate(prompts, sampling_params)\n\nfor output in outputs:\n    print(output.text)\n```\n\n### Serving with trtllm-serve\n\n```bash\n# Start server (automatic model download and compilation)\ntrtllm-serve meta-llama\u002FMeta-Llama-3-8B \\\n    --tp_size 4 \\              # Tensor parallelism (4 GPUs)\n    --max_batch_size 256 \\\n    --max_num_tokens 4096\n\n# Client request\ncurl -X POST http:\u002F\u002Flocalhost:8000\u002Fv1\u002Fchat\u002Fcompletions \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"model\": \"meta-llama\u002FMeta-Llama-3-8B\",\n    \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}],\n    \"temperature\": 0.7,\n    \"max_tokens\": 100\n  }'\n```\n\n## Key features\n\n### Performance optimizations\n- **In-flight batching**: Dynamic batching during generation\n- **Paged KV cache**: Efficient memory management\n- **Flash Attention**: Optimized attention kernels\n- **Quantization**: FP8, INT4, FP4 for 2-4× faster inference\n- **CUDA graphs**: Reduced kernel launch overhead\n\n### Parallelism\n- **Tensor parallelism (TP)**: Split model across GPUs\n- **Pipeline parallelism (PP)**: Layer-wise distribution\n- **Expert parallelism**: For Mixture-of-Experts models\n- **Multi-node**: Scale beyond single machine\n\n### Advanced features\n- **Speculative decoding**: Faster generation with draft models\n- **LoRA serving**: Efficient multi-adapter deployment\n- **Disaggregated serving**: Separate prefill and generation\n\n## Common patterns\n\n### Quantized model (FP8)\n\n```python\nfrom tensorrt_llm import LLM\n\n# Load FP8 quantized model (2× faster, 50% memory)\nllm = LLM(\n    model=\"meta-llama\u002FMeta-Llama-3-70B\",\n    dtype=\"fp8\",\n    max_num_tokens=8192\n)\n\n# Inference same as before\noutputs = llm.generate([\"Summarize this article...\"])\n```\n\n### Multi-GPU deployment\n\n```python\n# Tensor parallelism across 8 GPUs\nllm = LLM(\n    model=\"meta-llama\u002FMeta-Llama-3-405B\",\n    tensor_parallel_size=8,\n    dtype=\"fp8\"\n)\n```\n\n### Batch inference\n\n```python\n# Process 100 prompts efficiently\nprompts = [f\"Question {i}: ...\" for i in range(100)]\n\noutputs = llm.generate(\n    prompts,\n    sampling_params=SamplingParams(max_tokens=200)\n)\n\n# Automatic in-flight batching for maximum throughput\n```\n\n## Performance benchmarks\n\n**Meta Llama 3-8B** (H100 GPU):\n- Throughput: 24,000 tokens\u002Fsec\n- Latency: ~10ms per token\n- vs PyTorch: **100× faster**\n\n**Llama 3-70B** (8× A100 80GB):\n- FP8 quantization: 2× faster than FP16\n- Memory: 50% reduction with FP8\n\n## Supported models\n\n- **LLaMA family**: Llama 2, Llama 3, CodeLlama\n- **GPT family**: GPT-2, GPT-J, GPT-NeoX\n- **Qwen**: Qwen, Qwen2, QwQ\n- **DeepSeek**: DeepSeek-V2, DeepSeek-V3\n- **Mixtral**: Mixtral-8x7B, Mixtral-8x22B\n- **Vision**: LLaVA, Phi-3-vision\n- **100+ models** on HuggingFace\n\n## References\n\n- **[Optimization Guide](references\u002Foptimization.md)** - Quantization, batching, KV cache tuning\n- **[Multi-GPU Setup](references\u002Fmulti-gpu.md)** - Tensor\u002Fpipeline parallelism, multi-node\n- **[Serving Guide](references\u002Fserving.md)** - Production deployment, monitoring, autoscaling\n\n## Resources\n\n- **Docs**: https:\u002F\u002Fnvidia.github.io\u002FTensorRT-LLM\u002F\n- **GitHub**: https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FTensorRT-LLM\n- **Models**: https:\u002F\u002Fhuggingface.co\u002Fmodels?library=tensorrt_llm\n\n\n",{"name":5,"tags":23,"author":35,"license":14,"version":36,"description":7,"dependencies":37},[24,25,26,27,28,29,30,31,32,33,34],"Inference Serving","TensorRT-LLM","NVIDIA","Inference Optimization","High Throughput","Low Latency","Production","FP8","INT4","In-Flight Batching","Multi-GPU","Orchestra Research","1.0.0",[5,38],"torch","main","46e03791269608c5ac886a64c08f5d94147e8786","labs\u002F.codex\u002Fskills\u002Ftensorrt-llm","https:\u002F\u002Fgithub.com\u002Fbeyondai\u002Fsandbox","https:\u002F\u002Fgithub.com\u002Fbeyondai","2026-11-08 04:18:42",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add beyondai\u002Fsandbox --skill tensorrt-llm",{"tool":51,"command":52},"bunx","bunx skills add beyondai\u002Fsandbox --skill tensorrt-llm",{"tool":54,"command":55},"pnpm","pnpm dlx skills add beyondai\u002Fsandbox --skill tensorrt-llm","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbeyondai\u002Fsandbox\u002Fblob\u002Fmain\u002Flabs\u002F.codex\u002Fskills\u002Ftensorrt-llm\u002FSKILL.md",true,[59,65,69],{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fmulti-gpu.md","REFERENCE","参考文档",6699,"https:\u002F\u002Fgithub.com\u002Fbeyondai\u002Fsandbox\u002Fblob\u002Fmain\u002Flabs\u002F.codex\u002Fskills\u002Ftensorrt-llm\u002Freferences\u002Fmulti-gpu.md",{"path":66,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Foptimization.md",5613,"https:\u002F\u002Fgithub.com\u002Fbeyondai\u002Fsandbox\u002Fblob\u002Fmain\u002Flabs\u002F.codex\u002Fskills\u002Ftensorrt-llm\u002Freferences\u002Foptimization.md",{"path":70,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fserving.md",9798,"https:\u002F\u002Fgithub.com\u002Fbeyondai\u002Fsandbox\u002Fblob\u002Fmain\u002Flabs\u002F.codex\u002Fskills\u002Ftensorrt-llm\u002Freferences\u002Fserving.md",[74,81,88,95,102,109],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M7D3GMPGJZRG8EPY404YF8TR","weights-and-biases","Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform","https:\u002F\u002Fgithub.com\u002Fbeyondai\u002Fsandbox\u002Fblob\u002Fmain\u002Flabs\u002F.opencode\u002Fskills\u002Fweights-and-biases\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M7D3GFZH440V2J532BSZMPVP","serving-llms-vllm","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.","https:\u002F\u002Fgithub.com\u002Fbeyondai\u002Fsandbox\u002Fblob\u002Fmain\u002Flabs\u002F.opencode\u002Fskills\u002Fvllm\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"01M7D3GAE8MQCPGF72EP9G9GKY","verl-rl-training","Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.","https:\u002F\u002Fgithub.com\u002Fbeyondai\u002Fsandbox\u002Fblob\u002Fmain\u002Flabs\u002F.opencode\u002Fskills\u002Fverl\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":18},"01M7D3G7KKNE5RGNYJNXV4F0MM","unsloth","Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA\u002FQLoRA optimization","https:\u002F\u002Fgithub.com\u002Fbeyondai\u002Fsandbox\u002Fblob\u002Fmain\u002Flabs\u002F.opencode\u002Fskills\u002Funsloth\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":18},"01M7D3G2RCZQ08GS0KAW5CBWSC","fine-tuning-with-trl","Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO\u002FGRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.","https:\u002F\u002Fgithub.com\u002Fbeyondai\u002Fsandbox\u002Fblob\u002Fmain\u002Flabs\u002F.opencode\u002Fskills\u002Ftrl-fine-tuning\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":18},"01M7D3FX08BPB172CYGM597NZF","torchforge-rl-training","Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.","https:\u002F\u002Fgithub.com\u002Fbeyondai\u002Fsandbox\u002Fblob\u002Fmain\u002Flabs\u002F.opencode\u002Fskills\u002Ftorchforge\u002FSKILL.md",[],[]]