12 plugins from public Claude Code marketplaces. Each one bundles skills, slash commands, agents, hooks or MCP servers that install together.
Showing 12 plugins that match these filters.
mcpbundler-agent-skills-marketplaceeugenepyvovarov/mcpbundler-agent-skills-marketplace1Submit the repo with .claude-plugin/marketplace.json and we list every plugin.
Submit marketplacevLLM operator reference suite — deployment, configuration, quantization, caching, KV, tool parsers, reasoning parsers, chat templates, benchmarking, performance tuning, observability, omni, input modalities, speculative decoding, NVIDIA hardware, and a Gemma 4 31B operating-point serve recipe.
inferenceDeveloper tooling suite — BAML (typed LLM functions), Jinja2 templates (HuggingFace chat templates, Ansible), GNU Make best practices, and HuggingFace transformers config/tokenizer preflight (vLLM/sglang engine bridge).
developer-toolsOperate, configure, secure, and troubleshoot the LiteLLM AI gateway (proxy) and Python SDK: run the proxy (litellm --config), route to 100+ providers through one OpenAI-compatible API, configure model lists and routing/reliability, virtual keys, teams, budgets, rate limits, caching, guardrails, observability, and spend, and diagnose request failures. Use when deploying or running a LiteLLM proxy or gateway (config.yaml, ghcr.io/berriai/litellm), wiring the Python SDK or OpenAI SDK through it, or hardening a public-facing deployment. Do not use for operating a single inference engine (vllm, llama-cpp), for engine-selection methodology (ml-engineering), or for building applications on top of an LLM API (backend/frontend engineering).
Plan and execute production ML engineering work — classifier versus generative model selection, zero-shot baselines, coding specialization, model training and fine-tuning (LoRA/QLoRA), evaluation and eval-set design, quantization decisions, inference deployment, lineage, feature parity, drift response, and regression triage, experimental weight inspection and targeted editing, grounded in practical engineering patterns for production ML systems. Do not use for statistical modeling and experimental design (that's the data scientist) or for operating a specific inference engine (that's a tool skill such as llama-cpp or vllm).
Operate, configure, benchmark, and troubleshoot vLLM inference servers: Docker and Kubernetes deployment, quantization-aware model configuration (tensor parallelism, KV cache), OpenAI-compatible API serving, throughput and latency benchmarking, continuous batching tuning, GPU operation, and upgrade/rollback. Use when deploying or running a vLLM server (vllm serve, vllm/vllm-openai), sizing a model and its KV cache for GPUs, selecting quantization and parallelism, serving via /v1 endpoints, measuring serving throughput or latency, tuning batching, or diagnosing GPU, OOM, or startup failures in a vLLM deployment. Do not use for model training, fine-tuning, evaluation-set design, or engine-selection methodology (that is ml-engineering), or for operating the llama.cpp stack with GGUF models (that is llama-cpp); other inference engines (TGI, Ollama, Triton) are out of scope.
Inference KV-cache and transport suite — LMCache multiprocess (MP) standalone-server mode (DaemonSet + Deployment K8s pattern, ZMQ connector, L1 + L2 NIXL/POSIX/GDS/HF3FS/fs/s3/mooncake adapters) and NVIDIA NIXL transfer library (UCX/GDS/Mooncake/libfabric/HF3FS/S3 plugins, agent API, telemetry) used by Dynamo/vLLM/SGLang. Pairs with the vllm-caching skill in the `vllm` suite and sglang-hicache in the `sglang` suite.
inferenceInference host bring-up + tuning suite — Linux/GPU bare-metal host work that sits beneath any inference framework (vLLM, sglang, TensorRT-LLM). Two phases. Bring-up (nvidia-datacenter-bringup): Ubuntu 24.04 LTS from clean OS to gpu-operator cuda-validator passing — B300/B200/H100/A100/L40S/L4 driver + fabricmanager + NVLSM + DOCA-OFED install order, NVIDIA CUDA repo + DOCA repo + air-gap mirror, MOK + DKMS sign-on-build under Secure Boot, Dell PowerEdge XE9780/XE9785 baseboard firmware via iDRAC Redfish DellOemChassis.ExtendedReset, gpu-operator pre-installed-driver-mode integration. Tuning (gpu-host-tuning): read-only snapshot of CPU power state, C-states, NUMA topology, PCIe link state, GPU settings, kernel boot params, sysctl, ulimits, IRQ affinity, container runtime; optional pinned-host↔GPU memcpy bench (torch + numactl); per-lever cheat-sheets to flip settings (governor, EPP, cpuidle, persistence, ECC, hugepages, intel_iommu, NCCL env, tuned-adm profiles, BIOS guidance for Dell X
inferenceSGLang operator reference suite — HiCache (three-tier hierarchical prefix cache: GPU HBM → host DRAM → distributed L3 via Mooncake/3FS/NIXL/AIBrix/EIC/SiMM/file/LMCache) and the SGLang Model Gateway (`sgl-model-gateway`, formerly `sgl-router`) — Rust router fronting vLLM/SGLang inference workers on Kubernetes with cache-aware/prefix-hash/consistent-hash routing, K8s label-selector service discovery, PD-disaggregation, and `--enable-mesh` CRDT sync between gateway replicas. Pairs with the `vllm` suite for vLLM-side reference and `inference-cache` for engine-agnostic KV-cache transport.
inferenceNVIDIA AIPerf — vendor-neutral generative-AI inference benchmarking (the genai-perf successor): `aiperf profile` with concurrency / request-rate / fixed-schedule trace-replay / user-centric / multi-run-confidence load, 15 endpoint types and 6 custom dataset formats, goodput SLOs, GPU + Prometheus telemetry, and the reasoning-token TTFT/TTFO split — benchmarks vLLM / SGLang / TensorRT-LLM / Dynamo / NIM / Triton / Ollama.
inferenceServe vLLM presets on demand - locally, Kubernetes (KServe), Azure (Container Apps), AWS (ECS) or GCP (Cloud Run) - with their traces over OTLP, and tear them down again.
instrumentationPrepare a Linux server with NVIDIA or Intel Arc GPUs for LLM and neural-network workloads: NVIDIA driver + CUDA from the official repo or the in-tree Intel i915/xe driver with distro firmware, Docker Engine with verified GPU access (NVIDIA Container Toolkit or /dev/dri passthrough) as the mandatory base, staged verification gates for both vendors, optional docker-compose presets for vLLM, Infinity, OpenWebUI and Ollama plus Intel Arc stacks (llama.cpp SYCL/Vulkan, Ollama, OpenVINO, vLLM), GPU power limits persisted via systemd, case fans driven by GPU temperature and Intel Arc idle-power fixes (ASPM).
ops
Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.
