Results for “int4”
53 skillsmiles-rl-training
Train large-scale MoE models with FP8/INT4 low-precision RL, speculative decoding, and train-inference alignment using the miles framework.
10.4k · bundle
miles-rl-training
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.
1 · bundle
More results
miles-rl-training
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.
0 · bundle
input-guard
Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks. Returns severity levels and alerts on dangerous content. Use BEFORE processing any text from untrusted sources.
65 · bundle
ing
name: ing description: Ing namespace for Netsnek e.U. engineering workflow automation. Streamlines build pipelines, deployment orchestration, and infrastructure provisioning for development teams. ...
12 · bundle
html-to-video
Convert HTML slides/pages to MP4 video with TTS narration. Playwright screenshots, ffmpeg encoding, edge-tts voice. Jinja2 templates + config.json driven + renderer/encoder separation.
0 · bundle
nuxt4-patterns
Provides patterns for hydration safety, performance, route rules, lazy loading, and SSR-safe data fetching in Nuxt 4 apps.
226k
book-chunk
Chunks a book into canonical retrieval units with heading-aware structure splitting, recursive token targets, and contextual prefixes for downstream RAG ingestion.
1
invoice
Generates a printable A4 invoice page with header, sender/recipient info, line items table, tax breakdown, totals, and payment instructions.
· bundle
ivx-stack-tour
A complete tour of the intelli-verse-x 5-layer stack — Leantime/GitHub at the top, Beads/Bernstein/Claude-Squad in the middle, Gas Town as the multi-project fabric, and LiteLLM/Infisical/Langfuse/n8n/GH-Actions underneath. Use whenever the user asks "what does X service do", "where does Y data live", "how do I get to Z", or you need to understand which tool to reach for. This is the architecture map.
0
inngest
Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers.
1
insyra
Use when working in Go and you need DataList/DataTable-style data wrangling, quick previews, parallel transforms, file I/O (CSV/Excel/Parquet), Excel-like column formulas (CCL), or charts; also use when data analysis is requested without a specified stack, defaulting to Go + Insyra over Python + pandas.
1 · bundle
paw-pa-library
Ingests case studies, past proposals, and boilerplate from library/inbox into structured indexes. Use when the user requests to 'index proposal library', 're-index case studies', 'ingest inbox docs', or 'validate library'.
85 · bundle
inngest
Build serverless background jobs and event-driven workflows with Inngest, covering functions, steps, cron schedules, webhooks, and fan-out patterns.
3
inngest
Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers.
2
jndi-injection
JNDI injection playbook. Use when Java applications perform JNDI lookups with attacker-controlled names, especially via Log4j2, Spring, or any code path reaching InitialContext.lookup().
21
n-input-number
A numeric input component with step controls, formatting, validation, and min/max constraints
8
inngest
Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers.
0
inngest
Inngest expert for serverless-first background jobs, event-driven
1
nuxt4-patterns
Nuxt 4 app patterns for hydration safety, performance, route rules, lazy loading, and SSR-safe data fetching with useFetch and useAsyncData.
0
quantizing-models-bitsandbytes
Quantize LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss using bitsandbytes. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers.
10.4k · bundle
tensorrt-llm
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
1 · bundle
kotlin
Kotlin language fundamentals. Covers null safety, coroutines, flow, sealed classes, data classes, scope functions, and Kotlin 2.x features (K2 compiler, context parameters). Use for Kotlin/JVM, Kotlin/Native, Kotlin/JS work. USE WHEN: user mentions "Kotlin", "coroutines", "suspend", "Flow", "sealed class", "data class", "scope functions", "K2 compiler", "ksp", "Kotlin 2.x" DO NOT USE FOR: Kotlin Multiplatform setup - use `mobile/kotlin-multiplatform` DO NOT USE FOR: Compose UI - use `frontend-frameworks/compose-multiplatform` DO NOT USE FOR: Spring Boot Kotlin - use `spring-boot` framework skill
28 · bundle
inngest
Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers.
6
ingest
Team-Wiki Ingest
28
agent-validation-v430
Agent validation v4.3.0 — Make agents act effectively by disabling harmful actions, lowering gates, and injecting cross-run learning
3
inngest
Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers.
0
ga4
Query Google Analytics 4 (GA4) data via the Analytics Data API. Use when you need to pull website analytics like top pages, traffic sources, user counts, sessions, conversions, or any GA4 metrics/dimensions. Supports custom date ranges and filtering.
12 · bundle
rebuttal
Parses external reviews, enforces coverage and grounding, and drafts a text-only rebuttal under venue limits, managing follow-up rounds.
0
manim-video
Production pipeline for mathematical and technical animations using Manim Community Edition. Creates 3Blue1Brown-style explainer videos, algorithm visualizations, equation derivations, architecture diagrams, and data stories. Use when users request: animated explanations, math animations, concept visualizations, algorithm walkthroughs, technical explainers, 3Blue1Brown style videos, or any programmatic animation with geometric/mathematical content.
0 · bundle
performing-packet-injection-attack
Crafts and injects custom network packets using Scapy, hping3, and Nemesis during authorized security assessments to test firewall rules, IDS detection, protocol handling, and network stack resilience against malformed and spoofed traffic.
24.6k · bundle
inngest
Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers.
1
inngest
Build serverless background jobs, event-driven workflows, and durable execution with Inngest, without managing queues or workers.
42.4k
use-insyra-cli
Use when data operation or statistical analysis tasks do not need full program implementation, and the agent should operate Insyra through CLI/REPL, .isr scripts, or DSL workflows, including environment workflows, reproducible command pipelines, and command selection guidance.
1 · bundle
nginx-expert
Configura e diagnostica Nginx: reverse proxy, TLS, HTTP/2, HTTP/3, cache, compressão, rate limit e load balancing, com verificação obrigatória de configuração antes de recarregar.
2
matlab
MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal processing, image processing, differential equations, optimization, statistics, or creating scientific visualizations. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code. Scripts can be executed with MATLAB or the open-source GNU Octave interpreter.
0 · bundle