LLM inference and serving

Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.

sgl-project/sglang

Chooses the right serving container and current image URI for deploying a Hugging Face model to a SageMaker endpoint, preferring Hugging Face images over generic ones.

huggingface/skills

Delegate a coding task to Aider (aider) as a background implementer, then review its diff and land it yourself.

amElnagdy/delegate-skills

Runs evaluations of Hugging Face Hub models on local hardware with inspect-ai or lighteval, and helps choose between vLLM, Transformers and accelerate backends.

huggingface/skills

Diagnose and optimize vLLM Omni diffusion workloads, especially Wan/Qwen/Flux-style image and video generation.

vllm-project/vllm-omni

Runs the end-to-end vLLM Ascend release process: opens the release checklist and feedback issues, scans for release-blocking bugs and test coverage gaps, and generates release notes and announcements.

vllm-project/vllm-ascend

Autonomous performance optimization: research, PoC, benchmark, implement, review, PR

raullenchai/Rapid-MLX

Bump or upgrade the pinned versions of Helmor's bundled agent CLIs, SDKs, and supporting binaries — Claude Code + claude-agent-sdk (lockstep), Codex, Cursor SDK, OpenCode, Kimi, Pi, and gh / glab /…

dohooo/helmor

Run the pre-release end-to-end sweep of every user-facing surface — the 33 samples under samples/ (booted from their packaged artifacts and driven in a real browser via chrome-devtools MCP), the…

Atmosphere/atmosphere

Guides building on the 0G Compute Network, a decentralized GPU marketplace for AI inference and fine-tuning, with SDK patterns and CLI commands.

internet-court/internet-court-skill

Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release.

R6410418/Jackrong-llm-finetuning-guide

Fetch and diagnose vLLM Buildkite CI failure logs. An agent skill from guqiong96/Lvllm.

guqiong96/Lvllm

Create a new skill in the current repository. An agent skill from Hyk260/PureChat.

Hyk260/PureChat

Plans and audits Day-0 SGLang support for a new model release: scope, architecture gaps, PR order, validation gates and sanitized public evidence.

BBuf/AI-Infra-Auto-Driven-SKILLS

Deploys SageMaker endpoints with autoscaling, CloudWatch alarms and tags on by default, using scripts for real-time, scale-to-zero and async setups.

huggingface/skills

Work on vLLM-Omni quantization for diffusion, autoregressive, omni, or multi-stage models.

vllm-project/vllm-omni

Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven.

dstackai/dstack

Benchmark and compare LLM models for SUB/WAVE's on-air calls — track picks, segments, listener requests, DJ scripts, banter, and programme beats — in both candidate-pool and agent modes, using…

perminder-klair/subwave

Adapt AutoRound to support a new diffusion model architecture (DiT, UNet, hybrid AR+DiT).

intel/auto-round

Build, debug, and interpret vLLM GPU kernel microbenchmarks for CUDA, Triton, and CuteDSL, including CUPTI timing, correctness checks, generated-code inspection, multi-GPU measurements, and SOL…

guqiong96/Lvllm

Debug inference clients that use an attached provider and its native endpoint, including hosted APIs and host-local Ollama, vLLM, SGLang, TRT-LLM, LM Studio, or NIM.

NVIDIA/OpenShell

Reads SGLang or vLLM startup logs to show where GPU memory went and estimates how many concurrent requests fit at common token lengths.

BBuf/AI-Infra-Auto-Driven-SKILLS

Adapts and debugs Hugging Face or local models to run on vLLM with Ascend NPU, validates them by serving, and delivers the result as one signed commit.

vllm-project/vllm-ascend

Review pull requests and local branches for vllm-project/vllm-omni with a frozen snapshot, module-design ownership, feature-design overlays, targeted validation, and concise evidence-backed findings.

vllm-project/vllm-omni

Diagnose OpenAI-compatible model-serving failures from symptoms, endpoint reports, explicit configuration files, or logs while preserving evidence status and requiring confirm/refute checks.

Blackwellboy/model-serving-minefield

Profile AI inference workloads (vLLM, SGLang, TensorRT-LLM, PyTorch, any GPU application) with the Graphsignal profiler and read the results from its local /signals JSON endpoint.

graphsignal/graphsignal

A skill your agent uses when running, debugging, interpreting, or documenting mesh-llm benchmark tune model-serving throughput trials, including choosing…

Mesh-LLM/mesh-llm

Adapt AutoRound to support a new LLM architecture that doesn't work out-of-the-box.

intel/auto-round

驱动 One-Eval 对 API 或本地模型做端到端评测，覆盖纯文本、多模态、代码生成、函数调用和 Agent benchmark。当用户想评测模型在一个或多个 benchmark 上的表现、比较分数、补充 metric，或生成图文评测报告时使用本 skill。

OpenDCAI/One-Eval

Finds llama.cpp-compatible GGUF models on the Hugging Face Hub, picks a quantization for your hardware and launches them with llama-cli or llama-server.

huggingface/skills

Analyzes Torch Profiler traces from SGLang, vLLM and TensorRT-LLM servers into kernel attribution, overlap and fusion tables.

BBuf/AI-Infra-Auto-Driven-SKILLS

Processes sensitive local documents through PII Guard and a local Ollama model into a reversible redacted copy, without letting the main agent read the original or restored contents.

danyuchn/pii-guard

Inspects and tunes the shared-vs-dedicated memory split on AMD Ryzen APUs with unified memory (UMA) so larger LLMs and image-gen models fit on the iGPU, or so reserved GPU memory is returned to the…

amd/skills

A skill your agent uses for hipfire quant calibration, imatrix-driven experiments, KLD/PPL quality evaluation, k-map/format selection, MQ/HFQ/HFP/MFP tradeoff work, ParoQuant-style weight transform…

warpfront/hipfire

Use iDeer as a daily paper-reading workflow for chatbot-first users such as Codex, Gemini, or ChatGPT.

AI45Lab/iDeer

Diagnose and correct GPT-QModel tokenizer initialization, tokenization normalization, special-token handling, prompt rendering, and chat-template problems.

ModelCloud/GPTQModel

Run wally's LLM e2e on Apple Neural Engine (NeuRT) and Snapdragon Hexagon NPU (QHexRT) devices.

RunanywhereAI/wally

Add a new model export format to AutoRound (e.g., autoround, autogptq, autoawq, gguf, llmcompressor).

intel/auto-round

Adapt and port new LLM model architectures to this xinfer project.

guoqingbao/xinfer

Integrates a hosted API or local/open-weight model end-to-end across OpenTryOn (adapter, CLI registry, MCP, docs) and TryOn Studio (catalog, Connect keys, planner).

tryonlabs/opentryon

Check if package.json files are in sync with pnpm-lock.yaml.

Hyk260/PureChat

Query images with a local Ollama vision model without loading the image into the main agent context.

gridaco/grida

Build, extend, and debug AI agents in Egroo using the Microsoft Agent Framework (C .NET).

jihadkhawaja/Egroo

Answer questions about the user's own bank accounts and money using the bank MCP tools (listaccounts, getbalances, gettransactions, watches).

noskillish/bankmcp

Creates and validates dubbo-go-pixiu LLM gateway conf.yaml. An agent skill from apache/dubbo-go-pixiu.

apache/dubbo-go-pixiu

Add a new diffusion model (text-to-image, text-to-video, image-to-video, text-to-audio, image editing) to vLLM-Omni, including native non-Diffusers ports, reference-parity validation, Cache-DiT…

vllm-project/vllm-omni

Install, convert, debug, and benchmark sim2real ONNX GPU and TensorRT inference backends on onboard JetPack 5 Orin hosts such as g1-cable.

EGalahad/sim2real

A skill your agent uses when a user asks how many tokens (or how much context/cost) ContextPilot has saved, or wants a ContextPilot savings status/summary inside Hermes Agent — e.g.

EfficientContext/ContextPilot