“kernel”的搜索结果

Transfer known function and variable names from an older binary to a newer version. Compare disassembly and pseudocode with an LLM, produce structured mappings, and apply names and comments in IDA.

中文简介正在准备中。当前显示英语简介。

• Migrate known function names after a software update
• Locate kernel functions when the new PDB is unavailable
• Find updated function addresses and structure offsets

Measure denoising latency in SGLang diffusion models and identify slow operations with profiler traces. Compare performance and output quality on the same GPUs, check existing optimizations, and gather evidence before starting low-level kernel work.

中文简介正在准备中。当前显示英语简介。

• Measuring diffusion denoising latency
• Ranking slow operations from profiler traces
• Checking whether existing optimizations address a bottleneck

Analyze LLM serving traces to identify GPU time usage, opportunities to run operations concurrently, and known patterns for combining operations. Produce three consistent tables from saved traces or live captures on supported servers.

中文简介正在准备中。当前显示英语简介。

• Identify GPU operations that dominate inference time
• Compare input processing and token generation
• Trace GPU operations back to Python code

Investigate attempts to gain higher privileges on Windows and Linux using endpoint and security logs. Guide hypothesis testing, evidence analysis, false-positive checks, and reporting to help assess suspicious privilege changes and the scope of a compromise.

中文简介正在准备中。当前显示英语简介。

• Hunting for signs of privilege escalation
• Investigating alerts about suspicious privilege changes
• Assessing compromise scope during incident response

Create and tune Falco rules to detect possible container escapes, where a container gains access to its host. Define detection conditions, alert priorities, and output fields, then refine exceptions to reduce false positives.

中文简介正在准备中。当前显示英语简介。

• Writing rules for suspicious host filesystem access
• Investigating noisy container escape alerts
• Reusing detection conditions through macros and lists

Investigate malware hidden in boot records, UEFI firmware, or the operating system’s core. The skill guides evidence collection, boot integrity checks, firmware and memory analysis, and reporting of persistence mechanisms and remediation steps when compromise survives an OS reinstall.

中文简介正在准备中。当前显示英语简介。

• Investigating infections that survive an OS reinstall
• Examining unexplained Secure Boot integrity violations
• Finding hidden processes and suspicious kernel drivers

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

Create and refine Jupyter notebooks for experiments, exploratory analysis, or tutorials. Bundled templates help organize runnable code and short explanations into clear steps, while validation guidance supports notebooks that others can read and rerun.

中文简介正在准备中。当前显示英语简介。

• Starting a notebook for an experiment
• Turning scripts or notes into a structured notebook
• Creating a step-by-step teaching notebook

Inspect Mac performance to find processes using excessive CPU, GPU, memory, or energy. Combine measurements with explanations of known system processes to diagnose slowness, heat, and startup load, then recommend actions without changing system settings.

中文简介正在准备中。当前显示英语简介。

• Find the cause of a slow Mac
• Investigate loud fans and overheating
• Check memory pressure and swap activity

Turn mathematical claims into definitions, lemmas, and proofs for Lean 4 and Mathlib. Check proofs with Lean’s trusted core, separately review whether the formal statement matches the original claim, and record verification evidence.

中文简介正在准备中。当前显示英语简介。

• Verifying an important lemma with Lean 4
• Breaking a theorem into definitions and supporting lemmas
• Checking proofs for sorry, admit, and unauthorized axioms

Optimize and troubleshoot MNN's Hexagon DSP backend, which runs computation on a dedicated processor. The workflow uses device measurements to identify bottlenecks, compare v79 and v81 architectures, verify correctness, and investigate crashes or memory usage.

中文简介正在准备中。当前显示英语简介。

• Finding bottlenecks in Hexagon operators
• Checking changes on v79 and v81 devices
• Investigating cDSP crashes and device disconnects

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

Assess Docker, containerd, and Podman environments for weaknesses that could expose the host system. The skill organizes checks for excessive permissions, exposed runtime sockets, and known vulnerabilities, alongside indicators defenders can monitor.

中文简介正在准备中。当前显示英语简介。

• Assessing container isolation
• Reviewing permissions and exposed runtime sockets
• Checking known runtime vulnerabilities

Plan persistence testing for authorized Windows and Linux security exercises, examining how access can survive logons or restarts. The skill compares mechanisms by privilege level and environment, with validation steps, detection indicators, and cleanup considerations.

中文简介正在准备中。当前显示英语简介。

• Planning persistence tests for authorized exercises
• Comparing methods by operating system and privilege
• Reviewing detection indicators for persistence

Investigate how a limited Linux account could gain root, the system administrator's privileges. The skill guides checks of permissions, scheduled tasks, services, and known vulnerabilities, while outlining evidence defenders can monitor during authorized security assessments.

中文简介正在准备中。当前显示英语简介。

• Assessing Linux privilege escalation paths
• Practicing privilege escalation in CTF challenges
• Reviewing sudo and scheduled task configurations

Predict structures of protein, nucleic acid, and small-molecule complexes with ESMFold2, using single sequences or aligned related sequences. The skill also covers ESMC models for numerical sequence representations, mutation scoring, and predictions of contacts between residues.

中文简介正在准备中。当前显示英语简介。

• Predicting complex structures from single sequences
• Assessing designed binders with ESMFold2-Fast
• Predicting structures using aligned related sequences

Search Kaggle datasets, competitions, notebooks, and models through its official command-line tool. Download public data into a chosen directory and preserve audit records and file hashes, identifiers used to check downloaded files.

中文简介正在准备中。当前显示英语简介。

• Finding Kaggle datasets and inspecting metadata
• Downloading public data into a chosen directory
• Discovering competitions, notebooks, and models

Generate code for economics paper figures, including event studies that show effects over time and coefficient comparisons. Adjust fonts, colors, dimensions, and export settings, with consistent file naming for use in manuscripts.

中文简介正在准备中。当前显示英语简介。

• Plot treatment effects over time with confidence intervals
• Compare coefficient estimates across models
• Standardize figure formatting for a journal submission

Restructure claude-flow v3 into focused modules using Domain-Driven Design, which groups code by responsibility. Define module boundaries, event communication, and plugin interfaces to support a modular architecture with independently testable business logic.

中文简介正在准备中。当前显示英语简介。

• Split an oversized orchestrator into focused modules
• Define boundaries between tasks, sessions, and monitoring
• Design plugin extensions and domain events

Deploy code changes to a live hero training run by starting a new run from a permanent checkpoint, a saved training state. Compare matching training steps against agreed criteria and roll back if the trial fails.

中文简介正在准备中。当前显示英语简介。

• Deploy backend or optimizer changes to a live training run
• Compare loss and throughput across matching training steps
• Rehearse checkpoint handoff and rollback procedures

Automate forms, clicks, screenshots, and website checks in a browser where you are already signed in. A separately launched browser also supports scraping and network capture, while login or verification steps can be handed to a person.

中文简介正在准备中。当前显示英语简介。

• Fill forms on websites where you are already signed in
• Capture screenshots and check website behavior
• Record network traffic in a separately launched browser

Analyze CSV, Parquet, and JSON files to answer questions through grouping, joins, cleaning, time series, and charts. Chooses DuckDB or Polars and a suitable processing location based on the task and available memory.

中文简介正在准备中。当前显示英语简介。

• Summarizing and joining data files
• Exploring trends and distributions
• Cleaning data before analysis

Create and refine Jupyter notebooks for experiments, exploratory analysis, or tutorials. Bundled templates help organize runnable code and short explanations into clear steps, while validation guidance supports notebooks that others can read and rerun.

中文简介正在准备中。当前显示英语简介。

• Starting a notebook for an experiment
• Turning scripts or notes into a structured notebook
• Creating a step-by-step teaching notebook

Choose an NVSHMEM transport, the communication path between compute nodes, from installed plugins, network evidence, and optional workload analysis. Receive a recommended configuration with minimal environment variables, compatibility evidence, alternatives, and clearly stated unknowns.

中文简介正在准备中。当前显示英语简介。

• Choosing a transport compatible with a compute system
• Assessing communication needs in selected CUDA code
• Getting minimal transport selection settings