markfu909
Community@tianhao909
Agent Skills by markfu909
Showing 85 vetted skills indexed across 1 GitHub repositories.
tianhao909ml-paper-writing
Automates writing of ML/AI papers with LaTeX templates and citation verification.
tianhao909serving-llms-vllm
Serve LLMs with vLLM, PagedAttention, and continuous batching.
tianhao909tensorrt-llm
Optimize LLM inference on NVIDIA GPUs with TensorRT-LLM.
tianhao909sglang
Serve LLMs and VLMs with structured generation and RadixAttention prefix caching.
tianhao909llama-cpp
Run LLM inference on CPUs, Apple Silicon, and non-NVIDIA GPUs with GGUF quantization.
tianhao909lambda-labs-gpu-cloud
Deploy on-demand NVIDIA GPU cloud instances for ML training and inference.
tianhao909skypilot-multi-cloud-orchestration
Orchestrate machine learning workloads across AWS, GCP, Azure, and Kubernetes.
tianhao909modal-serverless-gpu
Deploy machine learning models as auto-scaling APIs on serverless GPUs.
tianhao909nemo-curator
Curate LLM training data with GPU-accelerated deduplication and filtering.
tianhao909ray-data
Process large datasets for machine learning with Ray Data.
tianhao909dspy
Build DSPy programs with signatures, modules, and automatic prompt optimization.
tianhao909guidance
Control LLM output with regex and grammars for valid JSON, XML, or code.
tianhao909outlines
Enforce JSON, XML, or code output formats using Pydantic models and grammars.
tianhao909instructor
Extract structured data from LLM responses into Pydantic models.
tianhao909audiocraft-audio-generation
Generate music and sound effects from text using Meta's AudioCraft library.
tianhao909blip-2-vision-language
Bridge frozen image encoders and large language models for vision-language tasks.
tianhao909segment-anything-model
Segment arbitrary objects in images using point, box, or mask prompts.
tianhao909clip
Classify images and match image-text pairs using OpenAI's CLIP model.
tianhao909stable-diffusion-image-generation
Generate images from text prompts using Stable Diffusion via HuggingFace Diffusers.
tianhao909llava
Combine large language models with vision encoders for image-based conversations and question answering.
tianhao909whisper
Transcribe and translate audio in 99 languages using OpenAI's Whisper model.
tianhao909implementing-llms-litgpt
Implement and train LLMs using LitGPT with LoRA/QLoRA fine-tuning.
tianhao909mamba-architecture
Implement Mamba selective state-space models with linear O(n) complexity.
tianhao909rwkv-architecture
Implement RWKV architecture with linear inference time and constant memory per token.