11 boosters for "pytorch" — open source, verified from GitHub, ready to install
Real-time monocular depth estimation using Depth Anything v2. Transforms camera feeds with colorized depth maps — near objects appear warm, far objects appear cool. When used for privacy mode, the blend mode fully anonymizes the scene while preserving spatial layout and activity, enabling security
Drive a profile → modify → benchmark → log → commit loop on a GPU kernel until it runs faster than the reference. The user provides at minimum a kernel; everything else (reference, inputs, bench script, hints) is optional. Does NOT apply when: Before doing anything else, establish the workspace — th
Query a structured, cross-referenced knowledge base of GPU kernel optimization for NVIDIA Blackwell (SM100) and Hopper (SM90). The repository update date is recorded in ; run for current corpus counts. Trigger this skill when the user asks about: Do NOT use this skill for:
Graphsignal observes inference workloads from a sidecar process — the profiler. It never shares a process with CUDA: the profiler watches the workload externally via CUPTI, OTLP/gRPC, Prometheus scraping, and NVML. Auto-instrumentation covers vLLM, SGLang, and PyTorch out of the box. Two install pat
Ray is an expert booster for Apache Ray distributed computing that helps developers convert Python code to Ray workloads, debug applications, and optimize performance across Ray's ecosystem (Core, Data, Train, Serve, Tune). Ideal for ML engineers and Python developers scaling computations from single machines to clusters.
"name": "inference-builder", "description": "Generate deployable Vision AI pipelines with high-performance video and streaming capabilities on NVIDIA GPUs. Create GPU-accelerated inference microservices using DeepStream, Triton, vLLM, TensorRT-LLM, or PyTorch backends.",
FHIRy is a Python package that converts FHIR healthcare data into pandas DataFrames, enabling data scientists and healthcare developers to perform analytics, machine learning, and AI on standardized health records. It's ideal for researchers and engineers working with health data who need quick, programmatic access to structured clinical datasets.
Lár Windsurf Rules is a cursor ruleset that guides developers in building graph-based AI agents using the Lár framework with strict typing, explicit node linking, and auditable patterns. It benefits developers building complex, self-correcting agentic systems who need clear structural guidelines.
Automates cleanup of JupyterHub Docker environments by stopping containers and removing orphaned resources. Ideal for data scientists and ML engineers managing local Jupyter development platforms who need to free up disk space and reset their environments.
An ML engineer agent that handles end-to-end production ML workflows including model serving, feature engineering, A/B testing, and monitoring for TensorFlow/PyTorch deployments. Ideal for teams building scalable ML systems who need guidance on MLOps best practices and production readiness.
Heuristic scoring (no AI key configured).
