「inference」の検索結果

Expert FinOps guidance for cloud, AI, and SaaS technology spend. Covers AI cost management, agentic FinOps, GenAI capacity planning, self-hosted vs managed inference, Anthropic billing, open-weight vendor APIs (DeepSeek, Qwen, Kimi, GLM), AWS (EC2, Bedrock, SageMaker, Savings Plans, CUR), Azure (reservations, AHB, OpenAI PTUs), GCP (Vertex AI, BigQuery), OCI, Kubernetes cost allocation, data platforms (Databricks, Fabric F-SKUs, Snowflake), tagging governance, SaaS management (SAM, shadow IT), AI coding tools (Cursor, Claude Code, Copilot, Codex), ITAM, allocation, showback, chargeback, anomaly management, KPIs and benchmarking, waste detection playbooks, workload onboarding and M&A, and GreenOps (cloud carbon, CSRD). Use for any question about technology cost or waste in your estate - expiring commitments or RIs, NAT gateway bills, idle VMs, snapshot sprawl - and for commitment sizing, rightsizing, allocation, SaaS sprawl, AI dev tool spend, or connecting spend to business value. Built by OptimNow.

日本語の概要は準備中です。原文の説明を表示しています。

Use when the user wants to run a diffusers pipeline from a terminal (one-off generation, batch jobs, smoke-testing a new model), run on HF Sandbox hardware via `--remote`, introspect a pipeline's input schema before calling it, or attach a LoRA at inference time. Prefer this over writing ad-hoc Python scripts for generation tasks.

日本語の概要は準備中です。原文の説明を表示しています。

Nature-style climate and ecology manuscript reviewer skill for testing biodiversity, ecosystem-function, carbon-cycle, conservation, global-change and ecological-inference claims against sampling, causal design, model structure, uncertainty and management scope.

日本語の概要は準備中です。原文の説明を表示しています。

Use when writing, reviewing, or optimizing CUDA kernels targeting sm_120a (RTX 5090 / Consumer Blackwell, GB202) in the imp inference engine. Triggers on CUDA/PTX kernel code, shared-memory layout, bank conflicts, tensor-core MMA (mxf4nvf4, tf32, 3xTF32/3xFP16), GEMV/GEMM/attention/quantization/GDN-scan kernels, decode tok/s under expected, kernel emitting HMMA instead of mxf4nvf4, occupancy, register pressure, __launch_bounds__, spills, PDL. Pair with `benchmark-cuda` for measurement and `check-degeneration` after hot-path changes.

日本語の概要は準備中です。原文の説明を表示しています。

Use when working on or testing imp-server and its HTTP APIs - OpenAI/Anthropic endpoints, /v1/chat/completions, /v1/messages, /v1/responses, SSE streaming, tool calling, json_schema/regex/GBNF constrained decoding, thinking/reasoning_content, cache_control/prefix cache, model loading and swapping, request priority, X-Request-Id, OTLP tracing / traceparent / Jaeger, /metrics, container env (IMP_SET), "server returns 404/garbage", API compliance. Do NOT use for CLI-only inference (imp-cli), kernel work (sm120-cuda-expert), or pure output-quality checks (check-degeneration).

日本語の概要は準備中です。原文の説明を表示しています。

Use when verifying that a model in the imp inference engine produces coherent output without repetition loops, token-stuck states, or state corruption across turns or streams. Triggers on "degenerates", "check degeneration", "repetition loop", "own own own", "stuck token", "empty content", "multi-turn regression", "does it still work", "NIAH", and after enabling CUDA graphs / changing forward pass / MoE routing / KV cache or KV dtype / GDN state or scan / sparse attention / PDL / speculation (MTP, n-gram) / ragged prefill / batched-decode kernels (smallm, producer quantize) / FA2 softmax.

日本語の概要は準備中です。原文の説明を表示しています。

Use when benchmarking, profiling, or A/B-testing CUDA kernels or end-to-end perf in the imp inference engine on RTX 5090 (sm_120), including refreshing tests/perf_baseline.json or publishing numbers to docs/BENCHMARKS.md and the README. Triggers on "benchmark kernel", "profile cuda", "ncu", "nsys", "kernel timing", "kernel sum", "occupancy", "bandwidth bound", "compute bound", "roofline", "perf baseline", "is this regression real", "decode dropped", "aggregate throughput", "two-image A/B", "prefill kernel A/B". Do NOT use for writing/optimizing kernel code (sm120-cuda-expert) or output-quality checks (check-degeneration).

日本語の概要は準備中です。原文の説明を表示しています。

Apply MCAF ML/AI delivery guidance for data exploration, feasibility, experimentation, testing, responsible AI, and operating ML systems. Use when the repo includes model training, inference, data science workflows, or ML-specific delivery planning.

日本語の概要は準備中です。原文の説明を表示しています。

Prevent AI hallucination and ensure evidence-based responses when analyzing code or making suggestions. Use when: analyzing code, making recommendations, providing options, or when user asks about confidence/certainty. Keywords: certainty, assumption, inference, evidence, source, 確定性, 推測, 假設, 來源, 證據.

日本語の概要は準備中です。原文の説明を表示しています。

用户需要从可观察的外部信号推断隐藏的内部状态时激活;当需要评估某人或某系统的整体状态但无法直接检测内部时; 当多个外部信号互相矛盾需要综合判断时。 典型触发信号: 用户说"怎么看出来这个人状态怎么样""从表面现象怎么判断内在情况""几个信号互相矛盾该怎么判断"。 不适用于: 可以直接测量/检测的场景(有体检数据、有监控面板、有可量化的指标), 或只有一个信号源且无法交叉验证的情况。

日本語の概要は準備中です。原文の説明を表示しています。

Generalised autonomous optimisation loop — soft RLVR for any artifact a user can measure. Use this skill whenever a user wants to iteratively improve an artifact — code, prompts, documents, configs, designs, content — by running structured experiments, evaluating results against a multi-dimensional rubric, and learning from each attempt. Triggers include: "optimise this", "keep improving until it's good", "run experiments on", "autoresearch", "iterate on this overnight", "try different approaches and pick the best", or any request implying repeated evaluate-and-improve cycles. Also use when the user wants to improve a system prompt, a data pipeline, a writing style, or any artifact where quality can be decomposed into measurable tracks. For inference optimisation tasks (model latency, throughput, quantization, GPU deployment), a* delegates the low-level tuning to AITune while maintaining quality tracking and learning.

日本語の概要は準備中です。原文の説明を表示しています。

Build a feature store using Feast for centralized feature management, configure offline and online stores for batch and real-time serving, define feature views with transformations, and implement point-in-time correct joins for ML pipelines. Use when managing features for multiple ML models, ensuring training-serving consistency, serving low-latency features for real-time inference, reusing feature definitions across projects, or building a feature catalog for discovery and governance.

日本語の概要は準備中です。原文の説明を表示しています。

Protein language models through the EvolutionaryScale `esm` Python SDK. Generate and embed sequences with ESM3 (multimodal sequence, structure and function prompting), extract per-residue and mean-pooled embeddings with ESM C, fold sequences with ESMFold2, and run inference locally or against the Forge and Biohub hosted clients. Use this skill for protein representation learning, variant effect and mutational scanning from likelihoods, sequence generation and inpainting, structure prediction from sequence alone, and embedding features for downstream models. Also trigger on esm, ESM3, ESMC, ESM Cambrian, ESMFold2, `from esm.models`, ESMProtein, GenerationConfig, forge.evolutionaryscale.ai, biohub.ai, or ESM_API_KEY.

日本語の概要は準備中です。原文の説明を表示しています。

DiffDock and DiffDock-L diffusion-based molecular docking. Use for blind protein-small-molecule pose prediction from a PDB file or sequence plus SMILES/SDF/MOL2, batch docking over a CSV of complexes, virtual screening triage, sampling multiple poses per complex, and reading the confidence score correctly. Also trigger on DiffDock, DiffDock-L, inference.py, confidence_model, samples_per_complex, ESM embedding preparation for docking, or blind docking without a defined box. Not for binding affinity prediction — the confidence score ranks pose plausibility, not potency.

日本語の概要は準備中です。原文の説明を表示しています。

Queries the NCATS Translator ARAX production API for bounded, typed, provenance-rich one-hop and endpoint-pinned two-hop biomedical knowledge-graph relationships. Use for Biolink-constrained RTX-KG2 lookup, explicit selected-provider ARAX federation, separate entity normalization, qualifier-aware graph traversal, and inspection of TRAPI edge bindings, publications, and knowledge-source provenance. Do not use for inference, ranking, open-ended pathfinding, clinical guidance, or sensitive queries.

日本語の概要は準備中です。原文の説明を表示しています。

Build type-safe validated forms using React Hook Form v7 and Zod v4. Single schema works on client and server with full TypeScript inference via z.infer. Use when building forms, multi-step wizards, or fixing uncontrolled warnings, resolver errors, useFieldArray issues, performance problems with large forms.

日本語の概要は準備中です。原文の説明を表示しています。

Aggregate DiT inference outputs into per-dimension VBench metrics via AISBench. Run after the quant-tuning-evaluate DiT workflow produces a directory of mp4s and the user supplies a VBench-1.0-mini JSON + pre-populated cache dir. Single mode (Standard).

日本語の概要は準備中です。原文の説明を表示しています。

Append a DiT-tuning round to history.yaml. DiT-side counterpart of the LLM-path accuracy_append.py; records practice.md5, inference_outputs, fp_baseline_outputs, and the scoring fields (scores / overall_score / loss_vs_baseline / is_satisfied) populated by quant-tuning-score-dit. Idempotent on practice_id.

日本語の概要は準備中です。原文の説明を表示しています。

Interactively gather parameters for `python -m cli.inference.throughput_optimizer`, generate a deployment simulation command, explain assumptions, ask for execution confirmation, then run the simulation and summarize the best parallel strategy. Use when the user wants to evaluate a model on one or more hardware profiles, compare hardware targets, compare aggregation versus disaggregation versus PD ratio optimization, choose TP/EP/MOE-DP search ranges, or obtain recommended concurrency, throughput, TTFT, and TPOT results from throughput modeling.

日本語の概要は準備中です。原文の説明を表示しています。

Interactively gather parameters for `python -m cli.inference.text_generate`, generate a concrete text generation simulation command, explain assumptions, ask for execution confirmation, then run the command and summarize performance metrics. Use when the user wants to validate a specific model, hardware profile, batch/query size, prefill or decode scenario, TP/DP/EP/MOE parallel strategy, profiling database, chrome trace, empirical metrics export, or a best row produced by throughput_optimizer.

日本語の概要は準備中です。原文の説明を表示しています。

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video

日本語の概要は準備中です。原文の説明を表示しています。

MATLAB R2026a workflow for signal processing, DSP, image processing, computer vision, lidar, medical imaging, deep learning, and AI-assisted reproducible experiments. Use for filters, spectrograms, wavelets, object detection, segmentation, classification, training, inference, and generated figures.

日本語の概要は準備中です。原文の説明を表示しています。

Idiomatic Go concurrency - sync primitives, channel semantics, the select statement, and the standard channel patterns (cancellation/done-channel, fan-out/fan-in, pipeline, or-done, context, worker-pool). Use when writing or reviewing Go that spawns goroutines, shares state, or coordinates over channels, even if the user never says "concurrency" - e.g. data races, deadlocks, goroutine leaks, sync/context/select usage, or "make this parallel". Distilled from luk4z7/go-concurrency-guide.

日本語の概要は準備中です。原文の説明を表示しています。

Review a Go design spec before implementation begins - dispatch a subagent that checks a design doc for completeness, consistency, and idiomatic Go (simplicity, small consumer-defined interfaces, explicit wrapped errors, context propagation). Use when a user has a Go spec to review, asks "is this spec ready?", or is about to implement from a written design. Distilled from spf13/go-skills and adapted to this repo's conventions.

日本語の概要は準備中です。原文の説明を表示しています。