Kernel Triton Writing

NVIDIA/TensorRT-LLM/.claude/skills/kernel-triton-writing

Çoklu dosya

NVIDIA· v1.0.0

ai-mlResmi

Resmi Sağlayıcı Skill'iView repo

ONLY for OpenAI Triton (@triton.jit) kernel development. NEVER use for CUDA C++ kernels, TileIR, or profiling tools (ncu, nsys). The user's request must involve Triton explicitly. Covers Triton-specific patterns: fused elementwise, reductions (softmax, LayerNorm, RMSNorm), tiled GEMM with triton.autotune, and flash attention. Workflow: design, write, verify (with fast-path for explicit requests).

Dosyalar13 dosya

SKILL.md343 satır

Loading editor…

Kurulum

Önerilen

Tek komut — ajanınız otomatik olarak devreye alır.

AI aracını seç

Kurulum komutunu görmek için yukarıdan bir AI aracı seçin.

veya

Manuel Kurulum

Daha fazla adım

Arşivi indirin ve dosyaları projenize manuel olarak ekleyin.

Skill detayları

Versiyonv1.0.0

YazarNVIDIA

Kategoriai-ml

Skill IDNVIDIA/TensorRT-LLM/.claude/skills/kernel-triton-writing

Dosyalar13 dosya

İlgili skill'ler

Ad Accuracy DebugDebug AutoDeploy accuracy regressions vs a reference score (PyTorch backend or published baseline). Use when an AutoDeploy model's eval score is significantly below the reference and the root cause is unknown.Ad Add Fusion TransformationClaude Code skill (trtllm-agent-toolkit): implement or extend TensorRT-LLM AutoDeploy fusion transforms under transform/library/ in a TensorRT-LLM checkout. Prefer existing kernels and custom ops; use Triton only when no viable existing-kernel path exists. Use ad-graph-dump for AD_DUMP_GRAPHS_DIR workflows. Covers TRT-LLM paths, registry, default.yaml registration, graph validation, tests, and a review checklist — without prescribing profiling tools or throughput targets.Ad Conf CheckCheck whether AutoDeploy YAML configs were actually applied by analyzing server logs and optionally graph dumps (AD_DUMP_GRAPHS_DIR). Use when the user wants to verify config application, debug config issues, or check if AutoDeploy transforms (piecewise CUDA graph, multi-stream, sharding, fusion, etc.) were applied or fell back. Triggers on: "check config", "verify config", "ad-conf-check", "were my configs applied", "config not working", "check if piecewise is enabled", "check log for config", Ad Graph DumpEnable and interpret TensorRT-LLM AutoDeploy FX graph text dumps via AD_DUMP_GRAPHS_DIR. Use when you need before/after graphs per transform, to locate subgraphs, or to confirm a rewrite ran. Paths and behavior are grounded in tensorrt_llm/_torch/auto_deploy (GraphWriter, BaseTransform). Complements ad-add-fusion-transformation.Ad Layer VisualizerVisualize a specific transformer decoder layer from an AutoDeploy FX graph text dump as a hierarchical DOT/PNG diagram. Optionally annotate nodes with actual GPU kernel names and durations from an nsys trace. Use when the user wants to visualize, inspect, or debug a layer in an AutoDeploy model graph dump. Triggers on: "visualize layer", "show layer", "graph of layer", "layer visualization", "dump graph layer". Assumes graph dumps already exist in a directory (produced by AD_DUMP_GRAPHS_DIR).Ad Model OnboardTranslates a HuggingFace model into a prefill-only AutoDeploy custom model using reference custom ops, validates with hierarchical equivalence tests.