vLLM · For data scientists

Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.

Orchestra-Research/AI-Research-SKILLs

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

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

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

guqiong96/Lvllm

Low-token Codex session/thread title organizer. An agent skill from David-Lzy/codex_session_renamer.

David-Lzy/codex_session_renamer

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

ModelCloud/GPTQModel

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

Plans memory headroom, works through out-of-memory failures and watches temperature and power during long ML training jobs on NVIDIA DGX Spark.

wshobson/agents

Review and upgrade MetaX model support against a target vLLM revision and installed MACA components, recursively including model-dependent attention and kernels.

MetaX-MACA/vLLM-metax

Add or update an in-repository vLLM-Omni model recipe with verified task, input, output, hardware, command, feature, and validation contracts.

vllm-project/vllm-omni

Quick-reference help for fine-tuning language models with Axolotl, covering YAML configs, FSDP, context parallelism, compressed saves and dataset formats.

Orchestra-Research/AI-Research-SKILLs

Write or review Triton kernels for vLLM, with practical guidance for generated-code inspection, launch grids, indexing, specialization, tuning, and representative performance validation.

guqiong96/Lvllm

Review and adapt vllmmetax/registry registrations, quantization configurations, CustomOps and kernel dispatch against a target vLLM revision and installed MetaX APIs.

MetaX-MACA/vLLM-metax

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

marin-community/marin

Produces ranked, evidence-grounded next steps when an ML experiment has stalled, drawing on a Leeroopedia knowledge base or on fetched docs and issues.

Leeroo-AI/superml

Review PRs and local changes for hsliuustc0106/vllm-rlt: Ouro engine and KV correctness, serving behavior, and BF16 accuracy/speed evidence.

ThinkFlowLab/vllm-rlt

Find evidence-backed simplification candidates in vLLM-Omni and, when requested, turn them into focused proposals or code changes.

vllm-project/vllm-omni

Checks training code, configs and math against documented framework behavior before an expensive run, citing a knowledge base or official docs for every claim.

Leeroo-AI/superml

Run, resume, monitor, diagnose, and report Quark Quant-Perf workflows for PyTorch and HuggingFace transformers models.

amd/Quark

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss.

Orchestra-Research/AI-Research-SKILLs

High-performance RLHF framework with Ray+vLLM acceleration. An agent skill from Orchestra-Research/AI-Research-SKILLs.

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

Guides reinforcement-learning research with torchforge, Meta's PyTorch-native library that keeps RL algorithms apart from infrastructure, including GRPO math-reasoning runs.

Orchestra-Research/AI-Research-SKILLs

Trains LLMs with reinforcement learning using verl, from ByteDance's Seed team, with GRPO, PPO and other algorithms and swappable training and rollout backends.

Orchestra-Research/AI-Research-SKILLs

Review and adapt MetaX attention backends, MLA, sparse indexers, cache layouts, and their kernel wrappers against a target vLLM revision and the actually installed MetaX component APIs.

MetaX-MACA/vLLM-metax

Analyze and optimize vllm-rlt inference performance using reproducible unprofiled benchmarks, paired ops-only/full profiles, source-level attribution, and correctness checks.

ThinkFlowLab/vllm-rlt

Audit and adapt monkey patches in vllmmetax/patch/ against a target upstream revision.

MetaX-MACA/vLLM-metax

Establish the shared environment, source/runtime correspondence, target confirmation and validation evidence for MetaX vLLM upgrades.

MetaX-MACA/vLLM-metax

This is a skill for benchmarking the efficiency of automatic prefix caching in vLLM using fixed prompts, real-world datasets, or synthetic prefix/suffix patterns.

vllm-project/vllm-skills

DESIGN a non-trivial codebase change (Harbor / MarinSkyRL / vLLM / OT-Agent / LLaMA-Factory) as a dependency-ordered STAGED PLAN before writing code — a feature port, a multi-step fix with parity…

open-thoughts/OpenThoughts-Agent

Trim large MetaX model directories for dummy smoke tests or real-checkpoint loading on limited GPUs.

MetaX-MACA/vLLM-metax

Diagnose and fix OCI AI Quick Actions (AQUA) issues including deployment failures, OOM errors, authorization problems, capacity issues, container errors, and policy misconfigurations.

oracle/accelerated-data-science

Upgrade vllm-omni NPU model runners (OmniNPUModelRunner, NPUARModelRunner, NPUGenerationModelRunner) to align with the latest vllm-ascend NPUModelRunner while preserving omni-specific logic.

vllm-project/vllm-omni

Given a .mlir file (or a directory of .mlir files) with TTIR ops, run the same TTIR normalization passes as D2MFrontendPipeline before D2M, then produce per-file outputs: preprocessed.mlir…

tenstorrent/tt-mlir

Profile vLLM and RT-VLM inference to identify and remove GPU-idle gaps, underfilled batches, transfer stalls, serialized multimodal work, scheduler gaps, or KV pressure.

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

Phase 1 of LLM deployment — for every leaf kernel × shape the model needs, verify numerical correctness on real NPU2 against the registry's GPU/vLLM-aligned standard.

Xilinx/mlir-air

EXECUTE a staged codebase plan (from code-create-staged-plan or an existing notes/<codebase/ plan) one stage at a time, gate-by-gate, while keeping the local clone ground truth and a dated…

open-thoughts/OpenThoughts-Agent

Interactive online benchmark orchestrator for vLLM inference services using vllm bench serve.

ascend-ai-coding/awesome-ascend-skills

Machine-learning research loop for dataset curation, fine-tuning, evaluation, inference deployment, experiment tracking, and model explainability.

AnastasiyaW/codex-claude-code-config

Build and operate Retrieval-Augmented Generation (RAG) infrastructure with vector stores, embedding pipelines, and hybrid search.

BagelHole/DevOps-Security-Agent-Skills

AISBench Benchmark - AI model evaluation tool for Ascend NPU.

ascend-ai-coding/awesome-ascend-skills

A skill your agent uses when choosing an open-weight LLM and clearing it for use — which family and size fit the task, the hardware and the budget, and above all whether the license permits shipping.

ericrisco/rsc-harness

Plan and execute production ML engineering work — model training and fine-tuning (LoRA/QLoRA), evaluation and eval-set design, quantization decisions, inference deployment, lineage, feature parity…

magnus919/agent-skills