AI & LLM Engineering · vLLM · For developers

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

Self-check your branch before creating a PR — catch dead code, prevent new model-specific Python examples, verify accuracy/perf claims, validate PR title format, and confirm merge readiness.

vllm-project/vllm-omni

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

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

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

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

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

BBuf/AI-Infra-Auto-Driven-SKILLS

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

ModelCloud/GPTQModel

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

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

apache/dubbo-go-pixiu

Always resolve Hugging Face models via model-shelf before any download.

alexziskind1/model-shelf

Build the standalone ZenDNN native library (zendnnl) from source with the alternate compute backends OFF (no oneDNN, libxsmm, parlooper, fbgemm), keeping AOCL DLP, which is the GEMM backend zendnnl…

amd/ZenDNN

Check model compatibility with xinfer before loading. An agent skill from guoqingbao/xinfer.

guoqingbao/xinfer

Uses the Outlines library to constrain model output to a JSON schema, Pydantic model, regex or fixed set of choices when running local models.

Orchestra-Research/AI-Research-SKILLs

Deploys LLMs with vLLM for high-throughput serving, covering the OpenAI-compatible server, offline batch inference, monitoring and a Docker rollout.

Orchestra-Research/AI-Research-SKILLs

Query Finelog logs and telemetry for Iris tasks, workers, profiles, training, vLLM, and cross-cluster forwarding.

marin-community/marin

Test LLM models served by xinfer for correctness, output quality, and performance.

guoqingbao/xinfer

Validate changed quantization math, packed formats, and inference kernels against a Torch oracle; adjudicate near-tie mismatches before rejecting optimized arithmetic.

ModelCloud/GPTQModel

Compose, edit, refactor, and validate Lego-RL train/eval/infer .env configs and reusable scripts/templates modules.

LegoX/Lego-RL

Integrate a new text-to-speech model into vLLM-Omni from HuggingFace reference implementation through production-ready serving with streaming and CUDA graph acceleration.

vllm-project/vllm-omni

Sets up a structured debugging session for a Dynamo bug — pull the report from a Linear ticket, GitHub issue, or pasted text, capture the environment, create a persistent worklog markdown file, and…

ai-dynamo/dynamo

Run vLLM performance benchmark using synthetic random data to measure throughput, TTFT (Time to First Token), TPOT (Time per Output Token), and other key performance metrics.

vllm-project/vllm-skills

Serves AI models on AMD Instinct GPU hardware using vLLM. An agent skill from amd/skills.

amd/skills

Deploy LLM models on OCI using AI Quick Actions (AQUA) - single model, multi-model, stacked (LoRA), with GPU shape selection, vLLM configuration, streaming, and tool calling.

oracle/accelerated-data-science

Build vLLM (CPU) end-to-end with the oneDNN + ZenDNN (zen64) backend via direct integration (NO zentorch).

amd/ZenDNN

Split a multi-call LM workflow by cognitive load, not by accuracy: let one strong model make the few reasoning decisions and a cheap model do the many mechanical executions (Aider architect+editor…

agentsope/SkillAlchemy

Run RecIF beam×concurrency eval and FlashRec vs SGLang/vLLM/TRT-LLM baselines.

sohu-mptc/FlashRec

Benchmark vLLM or OpenAI-compatible serving endpoints using vllm bench serve.

vllm-project/vllm-skills

verl-omni commit message + PR conventions and the mandatory contribution policy.

verl-project/verl-omni

Register, list, get, and manage LLM models in OCI AI Quick Actions (AQUA) using the ADS SDK.

oracle/accelerated-data-science

Bump Heron version via the VERSION-file SSOT. An agent skill from Netis/heron.

Netis/heron

A skill your agent uses when adding, debugging, or validating a bring-your-own VLM in VSS RT-VLM, including custom Hugging Face or NGC checkpoints, vLLM adapters or plugins, model shims, and…

NVIDIA-AI-Blueprints/video-search-and-summarization

Half-Quadratic Quantization for LLMs without calibration data.

Orchestra-Research/AI-Research-SKILLs

Covers serving LLMs with SGLang, whose RadixAttention reuses cached prefixes, and constraining output to JSON, regex or grammar for agent and tool-calling workloads.

Orchestra-Research/AI-Research-SKILLs

This is an experimental Skill. An agent skill from GoogleCloudPlatform/accelerated-platforms.

GoogleCloudPlatform/accelerated-platforms

Run and troubleshoot the inference backends on the DGX Spark pair that FastLLM proxies to — starting or stopping models with vLLM, SGLang or sparkrun, choosing memory and speculative-decoding…

azrtydxb/Fastllm-proxy