Development skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

perf-torch-cuda-graphs

Apply CUDA Graphs to PyTorch workloads — API selection (torch.compile, PyTorch make_graphed_callables, TE make_graphed_callables, MCore CudaGraphManager, FullCudaGraphWrapper, manual torch.cuda.graph), code compatibility, capture workflows, dynamic pattern handling, and troubleshooting. Triggers: CUDA graph, torch.cuda.graph, make_graphed_callables, reduce-overhead, graph capture, graph replay, kernel launch overhead, CudaGraphManager, FullCudaGraphWrapper, full-iteration graph, stream capture.

14.13k repo starsObserved in 4 repos
Development
GitHub

trtllm-code-contribution

Best practices for contributing code to TensorRT-LLM. Covers the official contribution process (issue tracking, fork workflow, DCO signing), coding guidelines, implementation workflow, common mistakes, testing strategy, commit hygiene, and review readiness. Incorporates rules from CONTRIBUTING.md and CODING_GUIDELINES.md plus lessons distilled from real PR retrospectives. Use when implementing new features, optimizations, or bug fixes in the TensorRT-LLM codebase.

14.13k repo starsObserved in 3 repos
Development
GitHub

trtllm-codebase-exploration

Systematic approach to exploring the TensorRT-LLM codebase before implementing new features or optimizations. Teaches how to discover existing infrastructure, trace code paths, and avoid reimplementing what already exists. Derived from real mistakes where ~250 lines of code were written and deleted because existing forward methods weren't discovered upfront. Use when starting any new feature, optimization, or code modification in TRT-LLM.

14.13k repo starsObserved in 3 repos
Development
GitHub

trtllm-flashinfer-upgrade

Upgrade flashinfer-python version in TensorRT-LLM. Fetches the latest releases from GitHub (stable and nightly), compares with the current pinned version, lets the user pick a target version, and updates all version references across the repo. Use when the user wants to bump or upgrade flashinfer.

14.13k repo starsObserved in 3 repos
Development
GitHub

ad-model-onboard

Translates a HuggingFace model into a prefill-only AutoDeploy custom model using reference custom ops, validates with hierarchical equivalence tests.

14.13k repo starsObserved in 2 repos
Development
GitHub

ad-sharding-ir-port

Adds sharding-aware IR hints (op substitutions, sharding kwargs, all_reduce insertions) directly into an existing AutoDeploy custom model (modeling_*.py). Edits the file in place — no separate _ir.py copy. Validates with apply_sharding_hints and end-to-end multi-GPU runs.

14.13k repo starsObserved in 1 repos
Development
GitHub

trtllm-model-onboard-multimodal

Onboard a HuggingFace multimodal model (vision/audio/video + text) to the TensorRT-LLM PyTorch backend. Use when writing a new `tensorrt_llm/_torch/models/modeling_<vlm>.py` plus its input processor and weight mapper, or extending an existing VLM. Not for AutoDeploy — use `ad-model-onboard` for that path.

14.13k repo starsObserved in 1 repos
Development
GitHub

trtllm-moe-develop

Review, design, and refactor TensorRT-LLM PyTorch MoE code for architecture fit, clean code, maintainability, and testability. Always use for any modification, review, refactor, or design planning that touches MoE modules, including tensorrt_llm/_torch/modules/fused_moe, ConfigurableMoE, MoE backends, MoEScheduler/moe_scheduler.py, forward execution/chunking, communication strategies, EPLB, quantization/weight handling, routing, factories, MoE docs, or MoE tests. Also use when the user asks whether a MoE design follows the current architecture or whether a MoE refactor is reasonable.

14.13k repo starsObserved in 1 repos
Development
GitHub

upgrade-oxc

Upgrade oxc, run codegen, and fix any breaking changes.

13.95k repo starsObserved in 5 repos
Development
GitHub

litestream

Expert knowledge for contributing to Litestream, a standalone disaster recovery tool for SQLite. Provides architectural understanding, code patterns, critical rules, and debugging procedures for WAL monitoring, LTX replication format, storage backend implementation, multi-level compaction, and SQLite page management. Use when working with Litestream source code, writing storage backends, debugging replication issues, implementing compaction logic, or handling SQLite WAL operations.

13.95k repo starsObserved in 2 repos
Development
GitHub