Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic...
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4Γ memory reduction with <2% perplexity...
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4Γ memory reduction with <2% perplexity...
Kubernetes node autoscaling and cost optimization with Karpenter. Use when implementing node provisioning, spot instance management, cluster right-sizing, node consolidation, or reducing compute...
Meta-skill for extracting and creating reusable Claude Code skills from past work sessions. Analyzes git history, code patterns, workflows, and documentation to identify harvestable skills, then...
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision...
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision...
3D HUD rendering with Three.js and TresJS for JARVIS AI Assistant
Expert in HUD animations, timing tokens, spring physics, reduced motion support, and creating purposeful interface animations
WebGL shaders and effects for JARVIS 3D HUD
Configure Frigate NVR with optimized YAML, object detection, recording, zones, and hardware acceleration. Use when setting up Frigate cameras, troubleshooting detection issues, configuring Coral...
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines -...
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines -...
This skill should be used when working with single-cell omics data analysis using scvi-tools, including scRNA-seq, scATAC-seq, CITE-seq, spatial transcriptomics, and other single-cell modalities....
This skill should be used when working with single-cell omics data analysis using scvi-tools, including scRNA-seq, scATAC-seq, CITE-seq, spatial transcriptomics, and other single-cell modalities....
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M...
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M...
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M...
Deep generative models for single-cell omics. Use when you need probabilistic batch correction (scVI), transfer learning, differential expression with uncertainty, or multi-modal integration...
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training