Loading...
Loading...
Found 10 Skills
Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.
Deploy and serve TensorFlow models
Convert HuggingFace transformer models to ONNX format for browser inference with Transformers.js and WebGPU. Use when given a HuggingFace model link to convert to ONNX, when setting up optimum-cli for ONNX export, when quantizing models (fp16, q8, q4) for web deployment, when configuring Transformers.js with WebGPU acceleration, or when troubleshooting ONNX conversion errors. Triggers on mentions of ONNX conversion, Transformers.js, WebGPU inference, optimum export, model quantization for browser, or running ML models in the browser.
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
Optimize Ollama configuration for maximum performance on the current machine. Use when asked to "optimize Ollama", "configure Ollama", "speed up Ollama", "tune LLM performance", "setup local LLM", "fix Ollama performance", "Ollama running slow", or when users want to maximize inference speed, reduce memory usage, or select appropriate models for their hardware. Analyzes system hardware (GPU, RAM, CPU) and provides tailored recommendations.
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
Export a promoted fine-tuned model in the right deployment format — merged safetensors, LoRA-only, GGUF with imatrix, or FP8. Use after a checkpoint passes promotion, when choosing a quantization format for a target device, or when an exported model fails its smoke test.
Create basic Transformers model adapters for msModelSlim. Implements required interfaces and completes a four-step verification workflow: generate test model -> full fallback quantization -> weight verification -> quantization description validation. Use this skill when the user wants to: (1) create msModelSlim adapters for decoder-only LLM, (2) adapt understanding VLM text backbones for quantization, (3) implement W8A8/W4A16 quantization workflow for new models. Trigger: user mentions "msModelSlim", "adapter", "model adapter","quantization", "W8A8","W4A16", "transformers", "LLM", "VLM", "adapter creation", "适配器","模型适配", "量化", "模型适配器", "LLM量化"
Analyze candidate models before adapter implementation. Determine model implementation source (transformers or model-local), structural features, layer-by-layer loading requirements, and MoE fused weight risks. Use this skill when the user wants to: (1) assess model adaptation feasibility before creating msModelSlim adapters, (2) analyze model structure and type classification, (3) evaluate MoE compatibility for quantization. Trigger: user mentions "model analysis", "msModelSlim", "adapter", "transformers", "MoE", "layer-by-layer", "model assessment", "feasibility", "模型分析", "适配可行性", "模型评估", "MoE分析"