Haopeng Chen
Community@arsity · University, MS 38677
CS PhD student
Agent Skills by Haopeng Chen
Showing 86 vetted skills indexed across 1 GitHub repositories.
arsityresearch
Automate AI/ML research workflows from paper discovery to BibTeX generation.
arsityml-paper-writing
Draft ML/AI papers with narrative frameworks and citation verification workflows.
arsityserving-llms-vllm
Deploy vLLM servers with OpenAI-compatible endpoints and tensor parallelism.
arsitytensorrt-llm
Optimize LLM inference throughput and latency on NVIDIA GPUs with TensorRT-LLM.
arsitysglang
Serve LLMs with RadixAttention prefix caching and structured JSON/regex outputs.
arsityllama-cpp
Run LLM inference on CPU, Apple Silicon, and consumer GPUs with GGUF models.
arsitylambda-labs-gpu-cloud
Provision on-demand GPU instances and multi-node clusters for ML training.
arsityskypilot-multi-cloud-orchestration
Orchestrate multi-cloud ML workloads with cost-aware scheduling.
arsitymodal-serverless-gpu
Provision serverless GPU capacity for ML workloads with Python-native definitions.
arsitynemo-curator
Filter, deduplicate, and sanitize large multimodal datasets for LLM training.
arsityray-data
Distribute and accelerate ML data processing with Ray Data.
arsitydspy
Compose declarative Language Model pipelines with DSPy modules and optimizers.
arsityguidance
Constrain LLM outputs with regex and grammar constraints.
arsityoutlines
Generate JSON/XML outputs constrained by FSM-based rules and JSON Schema.
arsityinstructor
Extract structured data from LLM outputs using Pydantic validation.
arsityaudiocraft-audio-generation
Generate music and sound effects from text prompts using AudioCraft models.
arsityblip-2-vision-language
Generate captions, answer visual questions, and retrieve images with BLIP-2.
arsitysegment-anything-model
Generate object masks from prompts using the Segment Anything Model.
arsityclip
Run zero-shot image classification and cross-modal retrieval with CLIP.
arsitystable-diffusion-image-generation
Generate images from text prompts using Stable Diffusion pipelines.
arsityllava
Integrate a vision encoder with a language model for image-grounded conversation.
arsitywhisper
Transcribe multilingual audio into text with timestamps and translation options.
arsityimplementing-llms-litgpt
Automate LLM implementation and experimentation workflows using LitGPT.
arsitymamba-architecture
Replace quadratic attention with Selective State Space Models for linear-time inference.