triton-sageattention
De la autor
Install Triton + SageAttention to accelerate ComfyUI (the sageattn attention_mode and inductor torch.compile used by WanVideoWrapper / many video graphs). Windows-first (triton-windows + woct0rdho prebuilt SageAttention wheels matched to torch/CUDA/python into the RIGHT python), plus Linux (official triton + build) and Mac (N/A → sdpa/MPS). Also covers the SAFE sdpa / no-compile fallback so an example that assumes sageattn + torch.compile still runs when these aren't installed (video-extend TRAP 5). Use when a loader crashes with "No module named 'sageattention'" or reports triton unavailable, when asked to speed up Wan/video workflows, or when deciding whether to install acceleration vs. fall back.
Instalare
npx skills add artokun/comfyui-mcp --skill triton-sageattention -a claude-code
Se instalează în .claude/skills/triton-sageattention/ · Fiecare comandă descarcă skill-ul direct de pe GitHub cu utilitarul open source skills.
Identic octet cu octet cu commit-ul scanat, cu licența depozitului și un fișier SOURCE.txt.
Vrei ca agentul să-ți propună skill-uri în timp ce scrii? Vezi cum folosești skill-urile din IDE.
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 87
aiqbench calculează scorul de încredere din semnale publice. Nu este un audit de securitate, așa că citește un skill înainte să-l instalezi.
Skill-uri similare
Cele mai apropiate de acesta prin ce fac și când sunt folosite.
- optimizing-attention-flashKalarisLabs/research-agent-skillsEnables Flash Attention for transformer models using PyTorch native scaled_dot_product_attention (PyTorch 2.2+) or the flash-attn library, including multi-query attention, sliding window attention, and FP8 on H100 (FlashAttention-3). Covers profiling speedup, checking accuracy against a baseline, and troubleshooting install and GPU support errors. Use when training or running transformers on long sequences (over 512 tokens), when standard attention runs out of GPU memory, when attention is the inference bottleneck, when switching a PyTorch model to the flash backend, or when tuning attention on H100 GPUs. Not for CPU inference, V100 GPUs, or sequences under 256 tokens; consider xFormers for other attention variants.Productivitate★ 61
- comfyui-launch-flagsartokun/comfyui-mcpPick the right ComfyUI startup flags for VRAM, attention, caching, and speed. The full decision matrix for OOM (--novram / --cache-none / --disable-smart-memory), shared-VRAM creep on Windows (--reserve-vram N), model-switching with big text encoders (--cache-none), high-VRAM throughput (--gpu-only / --highvram), and attention-backend selection (--use-sage-attention for speed, --use-pytorch-cross-attention as the highest-quality / Z-Image-safe fallback). Also the acceleration-stack + Blackwell/RTX 5000 (sm_120) notes. Use when a graph OOMs (especially long video like LTX 2 / WAN), when the GPU spills into shared VRAM and slows to a crawl, when switching between models eats all RAM, when Z-Image produces black/garbled output under Sage, or when deciding which attention backend to launch with. Flag names verified against upstream comfy/cli_args.py; see Sources.Browser★ 861
- swiftui-animation-matchRayFernando1337/rayfernando-skillsMatch UI/UX interaction needs to proven SwiftUI animation patterns from curated open-source catalogs. Use when planning or building iOS/macOS screens where an interaction should feel alive - loaders, likes, toggles, card decks, reveals, shaders - or when asked which animation fits a moment. Recommends system-first restraint before custom motion.Media★ 129
- huggingface-accelerateKalarisLabs/research-agent-skillsWraps existing PyTorch training scripts with HuggingFace Accelerate (Accelerator class, accelerate config, accelerate launch) so the same code runs on CPU, single GPU, multi-GPU, multi-node, TPU, or Apple MPS. Covers device placement, FP16/BF16/FP8 mixed precision, gradient accumulation, distributed checkpointing, and switching between DDP, DeepSpeed ZeRO, FSDP, and Megatron backends. Use when converting a single-GPU script to multi-GPU, enabling mixed precision, configuring DeepSpeed ZeRO or FSDP, or setting up gradient accumulation. Use when one script must run on different hardware. Not for callback-heavy training loops (use PyTorch Lightning) or multi-node orchestration with hyperparameter tuning (use Ray Train).Inginerie★ 61
- swift-expertJeffallan/claude-skillsBuilds iOS/macOS/watchOS/tvOS applications, implements SwiftUI views and state management, designs protocol-oriented architectures, handles async/await concurrency, implements actors for thread safety, and debugs Swift-specific issues. Use when building iOS/macOS applications with Swift 5.9+, SwiftUI, or async/await concurrency. Invoke for protocol-oriented programming, SwiftUI state management, actors, server-side Swift, UIKit integration, Combine, or Vapor.Planificare★ 12K
- safe-area-handlingCap-go/capgo-skillsFixes notch, Dynamic Island, home indicator, display cutout, and system bar overlap in Capacitor apps. Covers `viewport-fit=cover` + `env(safe-area-inset-*)`, the Capacitor 8 SystemBars core plugin (`insetsHandling`, injected `--safe-area-inset-*` CSS variables for Android WebView < 140, removal of `android.adjustMarginsForEdgeToEdge`), Android 15/16 enforced edge-to-edge (`overlaysWebView` and `backgroundColor` of @capacitor/status-bar no longer work at targetSdk 36), iOS `contentInset`, and insets that change at runtime on rotation, iPad/foldable resizable windows. Use when headers sit under the status bar, tab bars hide behind the gesture bar, `env()` returns 0 on Android, or layout broke after upgrading to Capacitor 8 / targetSdk 35+. Do not use for keyboard overlap (capacitor-keyboard), Ionic/Konsta component theming (ionic-design, konsta-ui), Tailwind utility setup (tailwind-capacitor), or iOS multi-window/resizability adoption (capacitor-ios-resizability).Design★ 73
Note și recenzii
—
nicio recenzie
Ai încercat acest skill? Notează-l ca să-i ajuți pe alții. Autentifică-te
Discuție
Intră în discuție. Autentifică-te