Waxell

skill

serving-llms-vllm Review findings

orchestra-researchorchestra-research/ai-research-skillsupdated

Browse GitHub Download zipBook a demo
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.
orchestra-research's own description, from the skill's files.
EngineeringResearchDocumentsskill
Stars
14,234
Version
v1
Copies
0
OverviewSecurity7Versions1

Overview

holdReview findings

Waxell's checks found 7 findings to review, highest severity high.

Highest severity
high
Findings
7
What ran
Static analysis

A clean result means nothing alarming in what is published, not a guarantee. How the checks work

We don't republish the skill's instructions. Read them on GitHub at the reviewed commit.

Security

Security scan

Checked 2 days ago

Result

Review findings Waxell's checks found 7 findings to review, highest severity high.

Checked with static analysis: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. Nothing was run. How the checks work

Findings (7)

high · 7

  • high

    Tells Claude to install unpinned packages (vllm)

    SKILL.md:19 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (locust)

    SKILL.md:97 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (locust)

    references/optimization.md:164 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (autoawq)

    references/quantization.md:204 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (auto-gptq)

    references/quantization.md:213 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (vllm)

    references/server-deployment.md:18 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (flash-attn)

    references/troubleshooting.md:193 · skill_risk:S2

Versions

Version history

Each distinct content we have seen, newest first, with the verdict it got at the time.

One version so far: v1 (1.0.0), seen 2026-11-03.

See and control which skills your people use

Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.

Book a demo

30 minutes. No commitment.

SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF

More engineering skills and plugins

See all