“compression”的搜索结果

Write and edit system prompts, tool instructions, and agent definitions with clear structure and explicit rule strength. It guides tag use, placement of critical constraints, concise wording, and practical examples that show how tools should be used.

中文简介正在准备中。当前显示英语简介。

• Drafting system prompts for agents
• Clarifying required and optional instructions
• Writing tool explanations with runnable examples

Parse Windows Prefetch files, which store traces of program execution, to extract run counts, timestamps, and referenced files. Build execution timelines and compare findings with other forensic evidence when investigating suspicious software or tool usage.

中文简介正在准备中。当前显示英语简介。

• Checking whether a suspicious program ran
• Building a timeline of investigative tool findings
• Investigating compression and file transfer tool usage

Compress LLM weights using HQQ quantization, which stores weights with fewer bits without calibration datasets. Follow workflows for precision settings, model saving, inference integration, and LoRA fine-tuning of quantized models.

中文简介正在准备中。当前显示英语简介。

• Compressing LLMs without calibration datasets
• Serving quantized models with vLLM or HuggingFace Transformers
• Comparing bit widths and inference backends

Compress large language models to 4-bit weights to reduce GPU memory use and accelerate inference. Covers loading compressed models, configuring quantization, and using Transformers or vLLM, with guidance on hardware requirements and backend choices.

中文简介正在准备中。当前显示英语简介。

• Running large models with limited GPU memory
• Compressing a model with domain-specific sample text
• Serving AWQ models with vLLM

Audit instructions and memory files loaded on every agent turn. Identify repeated rules, contradictions, outdated content, and material better moved into skills, then receive evidence-backed recommendations ranked by estimated token savings and change risk.

中文简介正在准备中。当前显示英语简介。

• Reduce the size of instructions loaded on every turn
• Find conflicting rules across instruction and memory files
• Identify workflow instructions to move into separate skills

Install rtk in NanoClaw agent containers to compress development command output and reduce token use. A Claude Code hook automatically routes Bash calls through rtk, with runtime checks to verify installation and a command to inspect savings.

中文简介正在准备中。当前显示英语简介。

• Reduce token use from development command output
• Automatically route Bash calls through rtk
• Configure rtk for multiple agent groups

Helps write and review Nginx configurations for websites and APIs. Covers forwarding requests to application servers, distributing traffic, HTTPS settings, caching, compression, and logs to support performance tuning and investigation of slow responses.

中文简介正在准备中。当前显示英语简介。

• Forward API requests to application servers
• Distribute traffic and handle backend failures
• Review HTTPS settings and access restrictions

Write and review launch prompts for agents working autonomously for hours or days. Define successful deliverables, excluded partial results, stopping rules, worker handoffs, and evidence-based review requirements so completion can be assessed against explicit criteria.

中文简介正在准备中。当前显示英语简介。

• Turning vague requests into precise task briefs
• Defining stopping rules for long autonomous runs
• Specifying deliverables for parallel workers

Design persistent agent memory that retains knowledge across sessions and retrieves relevant facts when needed. Compare storage approaches, track people and changing information, and plan memory consolidation and evaluation based on the kinds of questions the agent must answer.

中文简介正在准备中。当前显示英语简介。

• Retain user preferences across conversations
• Track people and entities consistently across sessions
• Retrieve facts valid at a specific point in time

Design how an AI agent edits its own working conversation history, choosing what to retain, rewrite, or remove. Covers safeguards, capacity monitoring, recovery after overflow, and the computing cost of changing earlier context.

中文简介正在准备中。当前显示英语简介。

• Designing agents that edit their own conversation history
• Preserving exact values during long tasks
• Recovering from context overflow

Plan and improve AI agent systems by managing the information models receive. This collection covers memory, agent coordination, tool design, context compression, evaluation, and the operating controls needed for reliable autonomous workflows.

中文简介正在准备中。当前显示英语简介。

• Planning information management for a new AI agent
• Investigating failures in long agent conversations
• Designing agent memory and multi-agent coordination

Use Memori through MCP, a protocol connecting agents to tools, to retrieve past decisions and preferences, summarize ongoing work, and resume after conversation compression. It also guides selective long-term memory storage and usage limit checks.

中文简介正在准备中。当前显示英语简介。

• Retrieve decisions and preferences from earlier sessions
• Review current work when starting a session
• Resume work after conversation context is compressed

Create a source-linked rollup of a selected batch of Obsidian wiki log entries. Preview the complete draft while preserving original entries and child pages, then optionally apply the rollup and its index updates together.

中文简介正在准备中。当前显示英语简介。

• Reviewing a batch of recent wiki log entries
• Condensing logs while preserving source references
• Previewing a rollup before applying it

Build distributable CARLA releases or asset packages containing selected maps and props. It prepares content for runtime use, checks output files, supports destination changes, and preserves native ROS 2 support when explicitly enabled.

中文简介正在准备中。当前显示英语简介。

• Create a full CARLA release archive
• Export Town02 as an importable asset package
• Preserve native ROS 2 support in a packaged build

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.

中文简介正在准备中。当前显示英语简介。

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

Compress large language model weights to four bits with AWQ, a method that uses model activation patterns to limit quality loss. Follow workflows for quantization, loading compressed models, and serving them with vLLM using less GPU memory.

中文简介正在准备中。当前显示英语简介。

• Running large language models with limited GPU memory
• Quantizing a model with domain-specific text
• Serving an AWQ model with vLLM

Apply HQQ quantization, which stores language model weights using fewer bits without calibration examples. Covers precision settings, inference backends, saving compressed models, deployment with HuggingFace Transformers or vLLM, and further training with LoRA.

中文简介正在准备中。当前显示英语简介。

• Compressing a model without calibration data
• Comparing 4-bit and 2-bit quantization settings
• Running quantized models with HuggingFace Transformers or vLLM

Convert, resize, and compress videos and images, including batches of files. Combine steps such as scaling and compression, specify output formats and quality settings, and check that the resulting files match the requested parameters.

中文简介正在准备中。当前显示英语简介。

• Convert AVI videos to MP4
• Batch-convert PNG images to JPG
• Resize and compress videos for sharing

Handle failed video encoding by checking available encoders, testing a short clip, and trying alternatives. The workflow covers copying without re-encoding, switching codecs, which define video compression, and using MoviePy as another processing option.

中文简介正在准备中。当前显示英语简介。

• Processing uploaded videos with unknown codecs
• Handling video conversion in containers with limited encoder support
• Testing encoding before a large batch

Audit TLS/SSL, the technology that encrypts network connections, across servers and mobile apps. The skill covers outdated protocols, weak encryption, certificate validation failures, known vulnerabilities, and replay risks, helping organize evidence and prioritize fixes.

中文简介正在准备中。当前显示英语简介。

• Auditing server protocols, encryption settings, and certificates
• Reviewing certificate validation in mobile apps
• Assessing TLS 1.3 replay risks and mutual authentication

Prepare 3D models for browser games by cleaning source assets, exporting GLB or glTF, and optimizing geometry and textures. It also guides collision shapes, distance-based detail levels, and runtime checks for the chosen engine.

中文简介正在准备中。当前显示英语简介。

• Preparing Blender models for browser games
• Reducing GLB or glTF asset size
• Planning collision shapes and distance-based model detail

Hardware compression offload with DOCA Compress on a BlueField DPU, ConnectX NIC, or host: DEFLATE compress and decompress, plus LZ4 decompress (stream and block; LZ4 encode is NOT supported), instead of CPU zlib / zstd. Trigger on "offload this gzip", "decompress incoming network data on the NIC", "compress task returns INVALID_VALUE on alloc_init", "submitted a task but no completion arrives", or "decompress LZ4 on the BlueField", even without naming DOCA Compress. Covers enabling compress-deflate, decompress-deflate, decompress-lz4-stream and decompress-lz4-block tasks on a doca_compress context, sizing source / destination doca_buf against the per-task cap query, mmap permissions, offload vs CPU decisions, a round-trip smoke, and DOCA_ERROR_* from Compress calls. Refuse and route elsewhere for zstd / Snappy / brotli, LZ4 encode (a CPU LZ4 library), pure mmap-to-mmap copies (doca-dma), or DOCA Core lifecycle internals.

中文简介正在准备中。当前显示原文说明。

Run `doca_bench` (DOCA 2.7.0 or newer) to measure throughput, bulk latency, precision latency, or maximum bandwidth for RDMA, Compress, AES-GCM, SHA, DMA, EC, Ethernet, Comch, or GPUNetIO on a host or BlueField Arm. Use it to discover enabled benchmark libraries, capture a reproducible command/version/device/environment baseline, compare stable runs against a declared tolerance, or diagnose configuration, device-binding, workload-precondition, and measurement failures. Trigger for requests such as measuring BlueField compression speed, NIC RDMA throughput, crypto latency, or a pre-upgrade baseline. Do not use for application end-to-end timing, custom benchmark code, DOCA installation, or binary patches.

中文简介正在准备中。当前显示原文说明。

HTTP/2 protocol-specific attack playbook. Use when the target supports HTTP/2 and you need to exploit binary framing, HPACK compression, h2c upgrade smuggling, pseudo-header injection, stream multiplexing abuse, or H2→H1 downgrade translation flaws.

中文简介正在准备中。当前显示原文说明。