Agent Skills by gagan114662
Showing 165 vetted skills indexed across 2 GitHub repositories.
gagan114662ml-paper-writing
Draft Machine Learning paper sections from research repositories and verify citations.
gagan114662serving-llms-vllm
Serve LLMs with vLLM's PagedAttention and continuous batching.
gagan114662tensorrt-llm
Optimize LLM inference on NVIDIA GPUs with TensorRT-LLM quantization and batching.
gagan114662sglang
Accelerate LLM inference serving with RadixAttention prefix caching for structured generation.
gagan114662llama-cpp
Run LLM inference on CPUs, Apple Silicon, and non-NVIDIA GPUs using GGUF quantization.
gagan114662lambda-labs-gpu-cloud
Provision on-demand and reserved GPU cloud instances for ML training.
gagan114662skypilot-multi-cloud-orchestration
Orchestrate machine learning workloads across multiple cloud providers with cost optimization.
gagan114662modal-serverless-gpu
Run serverless GPU compute for machine learning workloads with auto-scaling.
gagan114662nemo-curator
Curtate multimodal datasets for LLM training with GPU-accelerated deduplication and filtering.
gagan114662ray-data
Process large datasets with distributed streaming across CPUs and GPUs.
gagan114662dspy
Build DSPy programs with declarative signatures and automatic prompt optimization.
gagan114662guidance
Generate structured LLM output using regex and grammars in Python.
gagan114662outlines
Enforce JSON, XML, or regex output formats using Pydantic models and constrained sampling.
gagan114662instructor
Extract structured data from LLM responses using Pydantic models.
gagan114662audiocraft-audio-generation
Generate music and sound effects from text using AudioCraft.
gagan114662blip-2-vision-language
Generate image captions and answer visual questions with BLIP-2.
gagan114662segment-anything-model
Segment objects in images using points, boxes, or masks as prompts.
gagan114662clip
Classifies images into text-defined categories using OpenAI's CLIP model.
gagan114662stable-diffusion-image-generation
Generate images from text using Stable Diffusion via HuggingFace Diffusers.
gagan114662llava
Process image content for visual question answering and captioning.
gagan114662whisper
Transcribe and translate spoken audio across 99 languages using OpenAI's Whisper model.
gagan114662implementing-llms-litgpt
Implement, train, and fine-tune LLMs using the LitGPT framework.
gagan114662mamba-architecture
Implement a state-space model architecture with O(n) complexity for sequence modeling.
gagan114662rwkv-architecture
Provides linear-time sequential inference and infinite context length for RNN-Transformer hybrid models.