Vitel Phone integration. Manage data, records, and automate workflows. Use when the user wants to interact with Vitel Phone data.
Vitepress Config Creator - Auto-activating skill for Technical Documentation. Triggers on: vitepress config creator, vitepress config creator Part of the Technical Documentation…
Vitess best practices, query optimization, and connection troubleshooting for PlanetScale Vitess databases.
Review a PlanetScale Vitess database for safe migrations, deploy requests, schema recommendations, Insights, webhooks, and operational safety.
Visual integration tool for exploration of spatial single-cell data. Use for creating interactive visualizations and dashboards for multi-modal and spatial omics data.
Explain how grapes are grown — the vine's annual cycle, canopy and yield management, farming philosophies from conventional to biodynamic, vine age effects, and the history of…
Upload and replace 3D model assets to VIVERSE using pls-cli. Use when the task involves uploading .zip/.glb/.obj files to VIVERSE, replacing existing assets, managing model…
Pushes a draft from abstract toward concrete at two scales. Noun-level (replaces "dog" with "German shepherd," "customer" with "Sarah at JPMorgan's options-trading desk," "many"…
Vivocalendar integration. Manage data, records, and automate workflows. Use when the user wants to interact with Vivocalendar data.
Vivomeetings integration. Manage data, records, and automate workflows. Use when the user wants to interact with Vivomeetings data.
HER ADIMDA okunur. Vixrex asistan işinde ürünü bozmayı, ölü kod bırakmayı, kabuk/boş işlemi, plan sapmasını ve paralel yolu engeller.
薇娅 / Viya 的公开销售表达与文案能力蒸馏。聚焦品类：全品类、服饰、美妆、快消。 用途：为英文商品卖点、推荐理由、信任建立和短字符转化文案提供可追溯方法模块，不冒充本人。 当用户要求「用薇娅 / Viya的带货逻辑」「参考薇娅 / Viya的卖点表达」「viya selling perspective」时触发。
Use for publication figures in matplotlib or seaborn — styles, fonts, sizes, facets, export.
AI-powered product design tool for transforming sketches into full-fidelity 3D renders.
Управление рекламой VK Ads: создание кампаний, таргетинг, ретаргетинг, контекстные фразы, статистика, look-alike.
VK-Aufklärung und prozessuale Erledigung im Vergabenachprüfungsverfahren: Fragen der Vergabekammer beantworten, Akteneinsicht nach § 165 GWB nutzen, Abhilfe nach § 168 GWB…
Автоматический поиск клиентов (родителей) для репетитора по математике в группах ВКонтакте с умной фильтрацией и приоритизацией онлайн-запросов.
Spezialfall Blitzer- und Messverfahren: standardisiertes Messverfahren, Rohmessdaten-Recht des Verteidigers (BVerfG 2 BvR 1167/20), Verwertbarkeit, Beweisantrag…
Bussgeldverfahren Grundzuege: Anhoerungsbogen, Einspruch innerhalb 2 Wochen, Hauptverhandlung Amtsgericht, Rechtsbeschwerde OLG nach §§ 79 ff. OWiG.
Verkehrsrecht einfuehrend: Verkehrsstrafrecht (Trunkenheit § 316 StGB, Gefaehrdung § 315c StGB, Unfallflucht § 142 StGB), OWi (Bussgeldverfahren), Haftpflicht, Kasko,…
Spezialfall fiktive Abrechnung beim Totalschaden: Wiederbeschaffungswert minus Restwert, 130-Prozent-Grenze BGH, Verweisung auf guenstigere Reparaturen…
Поиск продуктов ВкусВилл, просмотр состава/КБЖУ, проверка наличия и создание корзины
Pick an action format (discrete bin, FAST, flow-matching, dual-system) and VLA family (RT-2, OpenVLA, π0, GR00T) for a robot task.
Use when an instance needs to define its own session goal — generates structured GOAL_PROMPT, saves to MySQL, copies to clipboard, displays in ASCII box. Alias for self-goal.
Für VLB-Katalog (Verzeichnis lieferbarer Bücher): ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Use when producing the final PVLDB version of an accepted VLDB paper, covering the volume-specific template, PDF/A compliance and font embedding, figure legibility floors, the…
Use when engineering reproducibility into a VLDB paper before submission, covering hardware and configuration disclosure, dataset and workload provenance, run-to-run variance in…
Use when reasoning about how PVLDB reviewing actually works, covering the rolling monthly pipeline, the roughly six-week review turnaround, the accept/revise/reject outcome space,…
Use when auditing a PVLDB submission before a monthly deadline, covering the mandatory abstract on the 25th, the CMT window, the 1st-of-month 5:00 PM Pacific cutoff, category and…
Use when deciding what lives outside a PVLDB paper's page budget, covering the rule that appendices count against the limit, the extended technical report on arXiv under…
Use when deciding whether a project belongs at VLDB and in which PVLDB category, applying the data-management-primitive test, choosing among Regular, EA&B, Scalable Data Science,…
Use when planning a VLDB project on the PVLDB rolling calendar, covering month-picking strategy, the volume-to-conference mapping and acceptance cutoff, budgeting a possible…
Use when revising a PVLDB paper's prose, covering the page-one contract for systems readers, scoping performance claims to measured regimes, stating design trade-offs instead of…
Use when working with ВЛК procedures — категорії придатності А/Б/В/Г/Д (наказ МО № 402), кроки (ініціювання → направлення → засідання → висновок → оскарження), строки (ієрархічно…
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or — from…
Adapt and debug existing or new models for vLLM on Ascend NPU. Implement in /vllm-workspace/vllm and /vllm-workspace/vllm-ascend, validate via direct vllm serve from /workspace,…
Run production vLLM benchmarks — `vllm bench` (serve, throughput, latency, sweep, startup, mm-processor), request-rate vs max-concurrency semantics, TTFT/TPOT/ITL/E2EL…
Operating-point reference for serving Gemma 4 31B on vLLM — TP sizing, max_model_len, max_num_seqs, gpu_memory_utilization, kv_cache_dtype, EAGLE3 spec-dec, chat_template choice.
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or — from…
vllm-mlx expert guidance — Apple Silicon native LLM inference server with MLX backend, OpenAI/Anthropic API, continuous batching, and model setup…
NVIDIA AI-hardware + vLLM-platform reference covering Hopper (H100/H200), Blackwell (B100/B200/B300) and Blackwell Ultra, Grace-Blackwell superchips and NVL72 racks (GB200,…
Observe production vLLM — `/metrics` Prometheus surface (V1 engine), SLO-driven alerting on TTFT/ITL/queue/KV/preemption/aborts/corrupted-logits, shipping Grafana dashboards in…
Add a new diffusion model (text-to-image, text-to-video, image-to-video, text-to-audio, image editing) to vLLM-Omni, including Cache-DiT acceleration and parallelism support (TP,…
Integrate with vLLM-Omni using the OpenAI-compatible API for text, image, video, and audio generation.
Contribute to vLLM-Omni by adding new model support, fixing bugs, or improving features. Use when integrating a new model into vllm-omni, setting up a development environment,…
Benchmark, profile, and tune vLLM-Omni diffusion models, especially Wan/Qwen/Helios style pipelines on GPU or NPU.
Guide for achieving optimal inference performance with vLLM-Omni diffusion models. Covers all lossless and lossy optimization methods (parallelism, torch.compile, CPU offload,…
Scale vLLM-Omni across multiple GPUs and nodes using tensor parallelism, pipeline parallelism, OmniConnector disaggregation, connector backends, and Ray.
Configure vLLM-Omni for different hardware backends including NVIDIA CUDA, AMD ROCm, Huawei NPU, and Intel XPU.
Generate and edit images with vLLM-Omni using models like FLUX, Stable Diffusion 3, Qwen-Image, GLM-Image, BAGEL, and Z-Image.
Transcribe speech, generate images from prompts, analyze video content, and convert between modalities using multimodal omni-modality models like Qwen2.5-Omni and Qwen3-Omni.
Optimize vLLM-Omni performance through benchmarking, TeaCache, Cache-DiT, quantization, CPU offloading, and parallelism tuning.
Use before submitting a PR to vllm-project/vllm-omni — self-check the branch against project conventions, catch dead code, verify accuracy/performance claims, and confirm merge…
Review PRs on vllm-project/vllm-omni by routing to the right domain skills, checking critical evidence, and focusing comments on blocking issues.
Scan pull requests of a specific type (e.g., new model support) from vLLM and vLLM-Omni repos, extract code review patterns and suggestions, then generate a specialized review…
Launch and configure vLLM-Omni API servers for production model serving. Use when starting a model server, configuring stage pipelines, setting up GPU memory, enabling…
Install and configure vLLM-Omni for omni-modality model inference. Use when setting up vllm-omni, configuring the environment, installing dependencies, resolving GPU driver…
vLLM PagedAttention KV-cache management for high-throughput LLM serving. Continuous batching, memory utilization, OpenAI-compatible API, and multi-LoRA serving patterns.
vLLM performance-tuning operator reference — tuning workflow (baseline → bottleneck → knob → re-bench), fused-MoE kernel autotune (`benchmark_moe.py` generates…
vLLM datacenter-GPU quantization — picking, configuring, troubleshooting NVFP4, FP8, MXFP4, MXFP8, AWQ, GPTQ, INT8, compressed-tensors, modelopt, quark on…