Agent SkillsAtlasBETASign in
Back to directory

Vllm Speculative Decoding

Agent skill
1 skill
READMEOverview ↓

Pick, configure, tune, monitor vLLM speculative decoding in production. Eleven SpeculativeMethod options (ngram, ngramgpu, medusa, mlpspeculator, draftmodel, suffix, eagle, eagle3, dflash, mtp, extracthiddenstates), --speculative-config JSON schema, which methods pair with which target model family, Prometheus acceptance metric surface, version gates (v0.11.1 EAGLE-3 preamble fix, v0.16 parallel drafting, v0.18 ngramgpu, v0.19 dflash and zero-bubble), composability with chunked prefill / PP / LoRA / FP8 / structured outputs, Arctic Inference plugin, where spec-dec stops paying at high batch.

Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI

Supported by the Atlas install prompt. Skill-specific requirements vary.

Skill stats

Skills1CategoryGeneralStars0

About this skill

Pick, configure, tune, monitor vLLM speculative decoding in production. Eleven SpeculativeMethod options (ngram, ngramgpu, medusa, mlpspeculator, draftmodel, suffix, eagle, eagle3, dflash, mtp, extracthiddenstates), --speculative-config JSON schema, which methods pair with which target model family, Prometheus acceptance metric surface, version gates (v0.11.1 EAGLE-3 preamble fix, v0.16 parallel drafting, v0.18 ngramgpu, v0.19 dflash and zero-bubble), composability with chunked prefill / PP / LoRA / FP8 / structured outputs, Arctic Inference plugin, where spec-dec stops paying at high batch.

Quick start

  1. Copy the install prompt. Use the green button above this README.
  2. Send it to your agent. Paste it into your coding agent’s chat and send.
  3. Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.

Installation guide →

Review, license & listing details
Review the source before using this skill

This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.

Automated security scan: Unavailable

Unsupported source URL

About scan coverage and limitations
Original listing metadata

Original name

vllm-speculative-decoding

Original description

Pick, configure, tune, monitor vLLM speculative decoding in production. Eleven SpeculativeMethod options (ngram, ngram_gpu, medusa, mlp_speculator, draft_model, suffix, eagle, eagle3, dflash, mtp, extract_hidden_states), `--speculative-config` JSON schema, which methods pair with which target model family, Prometheus acceptance metric surface, version gates (v0.11.1 EAGLE-3 preamble fix, v0.16 parallel drafting, v0.18 ngram_gpu, v0.19 dflash and zero-bubble), composability with chunked prefill / PP / LoRA / FP8 / structured outputs, Arctic Inference plugin, where spec-dec stops paying at high batch.

About this listing

Category
General
Reported license
Not specified
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.
KEEP EXPLORING

Related packs & skills

Browse category →

Finding related packs and skills…

Vllm Speculative Decoding | Agent Skills Atlas