312건 · 관련도순
Executa inferência de LLM em CPU, Apple Silicon e GPUs consumer sem hardware NVIDIA. Use para edge deployment, Macs M1/M2/M3, GPUs AMD/Intel ou quando CUDA não está disponível. Suporta quantização GGUF (1,5-8 bits) para redução de memória e aceleração de 4-10× vs PyTorch em CPU.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Formato GGUF e quantização llama.cpp para inferência eficiente em CPU/GPU. Use ao implantar modelos em hardware de consumidor, Apple Silicon, ou quando precisar de quantização flexível de 2-8 bits sem requisitos de GPU.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Reduza o tamanho de LLMs e acelere a inferência usando técnicas de pruning como Wanda e SparseGPT. Use para comprimir modelos sem retreinamento, alcançando 50% de esparsidade com perda mínima de acurácia, ou ativando inferência mais rápida em aceleradores de hardware. Cobre pruning não estruturado, pruning estruturado, esparsidade N:M, pruning por magnitude e métodos one-shot.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Judge performance or resource claims on real hardware: benchmark design or review, latency, throughput, memory or headroom numbers, and accept-or-reject decisions on optimizations. Not for refactors with no resource claim.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Integrate a GPU operator into ATREX with minimal source, compatible lazy APIs, hardware dispatch, atrex-prefixed kernels, one functional test file, and target-GPU validation.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design and implement unit, conformance, integration, timing, boot, trace, video, audio, and regression tests for EMULATORS processors, chips, peripherals, and complete machines. Use when creating a verification strategy for a new emulator, converting hardware documentation into tests, adding diagnostic programs or golden artifacts, measuring behavioral coverage, or proving that components interact correctly.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Implement or extend a reusable hardware chip and its machine-specific wiring in EMULATORS, including registers, pins or logical signals, clocks, state machines, memory-mapped behavior, side effects, interrupts, DMA or bus requests, serialization, introspection, and chip tests. Use when adding a controller, timer, PIA, PPI, UART, video or sound device, custom ASIC, register bank, or a variant of an existing chip.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Validate and implement Sinclair ZX Spectrum 16K/48K ULA and board-level behavior in the EMULATORS repository, including PAL/NTSC raster timing, bitmap and attribute fetches, FLASH/BRIGHT/INK/PAPER rendering, CPU clock generation, lower-RAM and I/O contention, floating bus, snow effect, DRAM addressing and refresh, port FE keyboard/tape/border/sound behavior, interrupts, and ULA revision boundaries. Use when Codex reviews or edits namespace ZXSPECTRUM ULA, ULARegisters, Memory, PortManager, Screen, Sound, Datasette, Z80 bus timing, raster, contention, or ZX Spectrum hardware tests.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Validate and implement Sinclair ZX Spectrum 48K ROM-visible behavior in the EMULATORS repository, including reset and restart vectors, IM1/NMI handling, keyboard scanning and repeat, beeper and tape routines, screen/printer output, channels and streams, BASIC tokenization and execution, expression evaluation, memory movement, system variables, calculator stack, floating-point formats, ROM traps, localized ROM selection, and firmware/hardware timing contracts. Use when Codex reviews or edits ZX Spectrum ROM loading, KERNAL-style traps, keyboard, tape, screen, printer, BASIC files, tokens, system variables, startup, interrupts, or compatibility tests.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Plan, scaffold, implement, and integrate a complete new emulated computer or console in the EMULATORS repository. Use when Codex creates a new machine, platform, hardware model, or emulator executable; decides which existing CPUs, chips, memory, I/O, video, sound, ROM, and framework classes to reuse or extend; or coordinates several emulator subsystems into a bootable tested system.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Detect bootkits such as BlackLotus and Bootkitty and Secure Boot bypass via DBX and binary checks.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use Intel CHIPSEC to assess platform firmware configuration, SPI flash write protection, BIOS lock, SMM/SMRR, and Secure Boot variable state, dump SPI flash, and triage UEFI variables for firmware-level threats.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Complete SolanaOS agent skill — install, configure, and operate the autonomous Solana trading runtime with Honcho v3 epistemological memory, multi-venue perp trading (Hyperliquid + Aster), on-chain intelligence with USD pricing, Telegram bot, gateway API, Tailscale mesh, hardware integration, and cross-session recall. Use when asked to install SolanaOS, query Solana blockchain data, manage wallets, run OODA trading loops, configure strategies, control BitAxe mining fleets, pair Seeker devices, or operate any SolanaOS runtime surface.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Generate formal IT/hardware purchase request documents from informal requirements. Use when creating purchase justifications, cost-benefit analyses, ROI calculations, vendor comparisons, or MARP presentation slides for management approval.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when designing, reviewing, modifying, migrating, optimizing, securing, operating, troubleshooting, or decommissioning data architectures across data model exploration, SQL, ISO SQL conformance, NoSQL, vector, graph, document, time-series, NewSQL, search, in-memory, SQLite, CDC/Debezium, DBMS storage/query/recovery internals, database incident prevention, hardware acceleration, cache, big-data, lakehouse, and warehouse systems.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when developing, reviewing, debugging, porting, or engineering Linux kernel device drivers, kernel modules, device tree bindings, bus clients, subsystem drivers, DMA/IRQ/memory paths, userspace interfaces, or hardware bring-up plans.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
I-A LLMs Large Language Models (LLMs) are extensive, general-purpose models that can be pre-trained and adapted for specific tasks.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Topics on Secure Hardware, Fall 2018 Decentralized Technologies Decentralized Finance MOOC, Fall 202
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Maintain IT asset inventory and configuration management database. Track hardware, software, and cloud resources. Use when managing IT assets.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Migrate a .NET 10 project or solution to .NET 11 and resolve all breaking changes. This is a MIGRATION skill — use it when upgrading from .NET 10 to .NET 11, NOT for writing new programs. USE FOR: upgrading TargetFramework from net10.0 to net11.0, fixing build errors after updating the .NET 11 SDK, resolving source-breaking and behavioral changes in .NET 11 runtime, C# 15 compiler, and EF Core 11, adapting to updated minimum hardware requirements (x86-64-v2, Arm64 LSE), and updating CI/CD pipelines and Dockerfiles for .NET 11. DO NOT USE FOR: .NET Framework migrations, upgrading from .NET 9 or earlier, greenfield .NET 11 projects, or cosmetic modernization unrelated to the upgrade. NOTE: .NET 11 is in preview. Covers breaking changes through Preview 3.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Documentation structure and maintenance rules for the Megahub project. Use whenever making user-facing changes — adding features, changing behavior, fixing hardware compatibility, or modifying configuration. Describes which files to update, the README structure, and writing style.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
FlutterSecureStorage (v10.x) for encrypted key-value storage of sensitive data using platform-native secure enclaves with biometric authentication support. Use this skill when storing OAuth tokens (access tokens, refresh tokens, ID tokens), API keys and secrets, user passwords or PINs, session tokens, encryption keys, private keys for cryptography, certificate data, biometric enrollment data, banking credentials, health data, or any sensitive information requiring platform-level encryption (iOS Keychain with Secure Enclave, Android Keystore with Hardware-backed keys). Supports Touch ID, Face ID, and Android biometric prompt integration. Handles biometric change invalidation (resetOnError), data migration from SharedPreferences/EncryptedSharedPreferences, Google Drive backup exclusion, automatic key rotation, configurable encryption algorithms (AES), and prevents data extraction even on rooted/jailbroken devices. Essential for authentication flows, secure credential management, or compliance requirements (PCI DSS, HIPAA, GDPR data protection).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when working with Device42 — device42 IT infrastructure management covering data center infrastructure management (DCIM), application dependency mapping, IP address management, and asset lifecycle tracking. Use when documenting data center rack layouts and power chains, mapping application dependencies and communication flows, managing IP address allocation and subnets, or tracking hardware assets from procurement through decommission.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on Hugging Face, port code onto ZeroGPU, fix a Space that won't build or run, or otherwise work with `hf spaces …`, `@spaces.GPU`, Space README frontmatter, or the `spaces` Python package.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.