Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Serve and batch LLMs with Ray 2.57 v1.0.0

Use this resource to serve an OpenAI-compatible LLM or run batch inference with Ray 2.57

New

  • 525 downloads
  • 216 likes
  • 101 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install ray-llm-serving-batch-inference

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent replaces outdated patterns (the archived ray-llm repository, YAML configs, renamed functions) with LLMConfig and build_processor from Ray 2.57. You get an up-to-date serving or batch configuration.

Mostly picked by

Updated November 2, 2026

Card for the “Serve and batch LLMs with Ray 2.57” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • AGENTS.md: rules by category, from serving to batch processing
  • references/batch-build-processor-renamed.md: renamed function; references/scale-prefix-cache-routing.md: prefix-cache routing

Good fit for

  • You want to expose a vLLM model behind an OpenAI-compatible API
  • You run a large batch of texts through an LLM

Not for

    Tags

    • ray
    • llm
    • vllm
    • inference

    About

    You say

    “Deploy a vLLM model behind an OpenAI-compatible API with Ray Serve.”

    Card for the “Serve and batch LLMs with Ray 2.57” skill

    Skill published by pproenca under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to serve an OpenAI-compatible LLM or run batch inference with Ray 2.57
    3. Review and adjust the result

    Content preview

    Files

    • AGENTS.md5.2 KB
    • assets/templates/_template.md1.1 KB
    • LICENSE1.1 KB
    • metadata.json2.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/_sections.md2.7 KB
    • references/api-endpoint-surface-cpu-validation.md1.7 KB
    • references/api-lora-dynamic-multiplexing.md1.2 KB
    • references/batch-build-processor-renamed.md1.5 KB
    • references/batch-concurrency-and-alternatives.md1.3 KB
    • references/batch-stage-configs-not-flags.md1.6 KB
    • references/place-accelerator-type-validated.md1.3 KB
    • references/place-engine-builds-pg.md1.8 KB
    • references/scale-autoscaling-deployment-config.md1.5 KB
    • references/scale-prefix-cache-routing.md1.4 KB
    • references/serve-builtin-not-handrolled.md1.5 KB
    • references/serve-deprecated-server-router.md1.4 KB
    • references/serve-model-id-vs-source.md1.3 KB
    • references/serve-ray-llm-extra-pins-vllm.md1 KB
    • SKILL.md6.8 KB

    Origin and licence

    Listed unmodified

    Author
    pproenca
    Source
    github.com/pproenca/dot-skills/tree/cf93c57cac89d6fc3e4194686000411567f5caf3/skills/.experimental/ray-llm
    Licence
    MIT

    Notice

    « ray-llm » (pproenca, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.