Results for “servicem8”

Migrates legacy AEM (6.x, AMS, on-prem) to AEM as a Cloud Service using BPA CSV or CAM/MCP target discovery, with one-pattern-per-session workflow for scheduler, replication, event listener, HTL lint, dialog, and custom widget migration.

Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Deploy and serve LLMs with high throughput using vLLM's PagedAttention and continuous batching. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism for production inference.

Implements service mesh with Istio or Linkerd, covering traffic management, mTLS, circuit breakers, and observability for microservices on Kubernetes.

Model Context Protocol server exposing 53 tools, 3 resource types, and 3 prompts for AI agent consumption — quoting, building transactions, fee management, analytics, AMM operations, social fees, wallet operations over stdio transport.

Idefics2: An 8B Parameters Multimodal Model

Manage n8n workflows, executions and credentials via REST API

Authorized security assessment for cloud, container, and Kubernetes environments covering metadata SSRF, IAM misconfigurations, container escape paths, and cluster RBAC review.

Routes tasks to specialized agent offices and applies behavioral science frameworks to every output, with confidence tagging and session memory.

Expert en service mesh (Istio, Linkerd, mTLS, traffic management, observabilité, contexte DZ)

Checks on-chain agent trustworthiness, discovers agents for tasks, profiles agents, looks up wallet/identity records, contacts or dispatches agents, and reads or writes hosted metadata via the 8K4 Protocol (ERC-8004).

Senior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD). Decades of experience writing reliable, optimized, and maintainable embedded code with deep expertise in memory barriers, DMA/cache coherency, interrupt-driven I/O, and peripheral drivers.

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Manage multiple n8n instances over MCP by discovering, switching, and verifying the target instance before reads and writes.

service-development

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Drive Soup (`soup-cli`), a CLI-first tool for fine-tuning and post-training LLMs with one YAML config and one command — SFT, DPO/GRPO/ORPO/SimPO/KTO, QLoRA/DoRA/LoRA+, layer streaming for 4-8 GB GPUs, eval-gated training, and serving. Use when the user wants to `soup init`/`soup train` a model, pick a training method or quantization scheme, estimate cost/memory before training, fine-tune on a small local GPU, migrate a config from Axolotl/LLaMA-Factory/Unsloth, or serve/merge/push a trained adapter. Triggers on: "soup-cli", "soup train", "soup init", "fine-tune an LLM locally", "QLoRA on a laptop GPU", "layer streaming", "soup advise", "soup autopilot", "DPO/GRPO/ORPO training", "merge LoRA adapter".

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

vLLM: high-throughput LLM serving, OpenAI API, quantization.

Design and implement real-time audio processing chains using Audio Toolbox streaming objects. Use when building frame-based audio processing loops, multiband filters, dynamic range control, parametric EQ, level metering, loudness metering, SPL metering, octave-band analysis, sample rate conversion, frequency-domain filtering (long impulse responses, custom filter banks), or audio chains in Simulink. Covers visualization (visualize method), interactive tuning (parameterTuner), MIDI control, and Audio Toolbox Simulink blocks. Use when the user says "real-time audio", "streaming audio", "audio filter", "compressor", "equalizer", "level meter", "loudness meter", "SPL meter", "octave bands", "crossover filter", "audio chain", "MIDI control", "convolution reverb", "impulse response streaming", "frequency-domain filter", or asks to process audio frame-by-frame.

Enables decoupled pub/sub messaging between ViewModels using CommunityToolkit.Mvvm Messenger, covering weak/strong references, request/reply patterns, channel tokens, and lifecycle management.

Serve LLMs and VLMs on NVIDIA Jetson devices using vLLM or SGLang with optimized Docker containers and quantization presets.

Optimizes hot-path scalar loops in .NET 8+ with cross-platform Vector128/Vector256/Vector512 SIMD intrinsics, or replaces manual math loops with single TensorPrimitives API calls.

Build workflow automations with n8n. Use when a user asks to automate business workflows, connect APIs visually, build integrations between apps, self-host a Zapier alternative, or create data pipelines with a visual editor.

【稷下】SKILL.md — 技能清单 v1.0

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

SKILL.md — 硅基生命训练学·索引技能

Use when SWMM integration, API development, or data synchronization is needed. This agent specializes in SWMM connectivity within the IntegrateForge AI ecosystem.

Query 40+ bioinformatics services (UniProt, KEGG, ChEMBL, Reactome) with a unified Python interface for cross-database analysis, identifier mapping, and sequence analysis.

Self-hosted AI gateway with one OpenAI-compatible endpoint for multi-provider LLM, embedding, image, and audio routing, automatic fallback, load balancing, and cost optimization.

Server-Sent Events for real-time server-to-client streaming. Express, Fastify, FastAPI, Spring WebFlux SSE implementations. Event streams, reconnection, and EventSource API. USE WHEN: user mentions "SSE", "Server-Sent Events", "EventSource", "event stream", "text/event-stream", "live feed", "streaming updates" DO NOT USE FOR: bidirectional communication - use `socket-io`; WebRTC - use `webrtc`; LLM streaming - use AI SDK skills

Use when running HMMER master or worker daemon services that front `phmmer`, `hmmsearch`, and `hmmscan` against cached databases.