'triton' 검색 결과

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the user does not name it: verify operator step sequence, detect missing or out-of-order SOP steps, score factory/work-cell video for procedure compliance, run VLM-based SOP checking on industrial cameras, or call /v1/chat/completions with a file, RTSP, or Basler camera. Also trigger for its internals: SOPVideoProcessor, DeepStream GEBD model (e.g. DDM) via Triton CAPI, nvds_custom_postprocess, Cosmos Reason 1/2 vLLM, SSE streaming, Kafka NvProto/JSON output, Basler/Pylon camera + emulation, Docker compose, chunk-level latency. Do NOT trigger for generic DeepStream pipelines, object detection/tracking, NIM imports, or video summarization.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

算子级开发与性能优化：Triton / Ascend C / Catlass / PyPTO / TileLang 算子 编写、精度对齐与性能调优。优先路由到外部 cannbot-skills 技能库（不重复其内容）， 本 skill 只保留场景 → skill 映射与 MindIE-SD 特有补充。 当用户需要新增/优化算子、定位算子性能或精度问题时使用此 skill。 即使用户只提到"写个 triton kernel"或"这个算子怎么加速"而未说算子，也应触发； pattern 融合/编译后端见 pattern-dev，算子基准选型/接入测试见 benchmark-dev。 由 dev-workflow 或 pattern-dev 的 replacement kernel 场景触发。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Set up machine learning training and inference on NVIDIA DGX Spark. Get guidance on choosing containers and packages, resolving CUDA compatibility errors, and checking that PyTorch can access the GPU before starting a workload.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up a new DGX Spark for training or inference
• Diagnosing CUDA compatibility and import errors
• Choosing between containers and direct pip installation

Develop attack detection for SCADA systems that monitor and control industrial equipment. Compare network traffic and process measurements with normal behavior to identify unauthorized commands, altered sensor data, communication disruption, and indicators of known industrial malware.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Introducing intrusion detection in a SCADA environment
• Investigating suspected attacks on industrial control systems
• Creating detection rules for industrial protocol abuse

Reduce the memory needed to run large language models with GPTQ quantization, which stores model weights at lower precision. Covers loading compressed models, quantizing your own models, choosing execution backends, and connecting to memory-efficient fine-tuning.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run a language model within limited GPU memory
• Load a pre-quantized model for text generation
• Quantize and save your own trained model

Compress large language models to 4-bit weights to reduce GPU memory needs and accelerate text generation. Covers loading compressed models, converting your own models, choosing settings, and preparing memory-efficient fine-tuning with transformers and PEFT.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run language models with limited GPU memory
• Convert your own model to 4-bit weights
• Compare compression settings for quality and speed

Deploy ML models on Kubernetes with KServe (formerly KFServing) and NVIDIA Triton Inference Server. Includes canary deployments, autoscaling, model versioning, A/B testing, and GPU resource management for production model serving.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Provides guidance for writing, optimizing, and benchmarking Triton kernels for Intel XPU GPUs (Battlemage/Arc Pro B50) using the Xe-Forge optimization framework. Includes an LLM-driven trial-loop workflow (analyze, validate, benchmark, profile, finalize), XPU-specific patterns (tensor descriptors, GRF mode, tile swizzling), KernelBench fused kernels, and Flash Attention.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline injection.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

LLM and ML model deployment for inference. Use when serving models in production, building AI APIs, or optimizing inference. Covers vLLM (LLM serving), TensorRT-LLM (GPU optimization), Ollama (local), BentoML (ML deployment), Triton (multi-model), LangChain (orchestration), LlamaIndex (RAG), and streaming patterns.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Pre-execution Solana transaction streaming via Jito ShredStream, Shyft RabbitStream, and Triton Deshred

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Think and work like an expert MLOps Engineer. Use when a task calls for MLOps Engineer judgment. Reasons from data contracts, feature parity, evaluation gates, and rollback-readiness through MLflow/W&B registries, Feast feature stores, KServe/Triton serving, Great Expectations/TFDV validation, and Evidently PSI/KS drift monitors while treating train-serve skew, data leakage, silent degradation, and schema/concept drift as first-class failure modes.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Compile, profile, diagnose, optimize, and compare Ascend NPU operators across CANN versions and A2/A3/A5 for Ascend C, CATLASS, Triton-Ascend, TileLang-Ascend, PyPTO, and SHMEM/MC2. Use when an operator already has a runnable implementation and the user asks for msOpProf collection, bottleneck analysis, source-level tuning, or a reproducible before/after performance report. Do not use as the primary workflow for operator creation, migration, or unresolved correctness failures.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.