speculative-decoding

speculative-decoding is a skill for Claude Code, Codex from synthetic-sciences/openscience. It costs 77 tokens per session (3,759 once invoked), scanned A, a copy of speculative-decoding, Apache-2.0.

A collection of techniques that use a smaller draft model or extra prediction heads to help a larger language model produce tokens faster.

In plain words
What is it for?
Use it to speed up chatbots, code generation, and high-volume language-model serving, including deployments on limited hardware.
Why use it?
It can reduce response time and increase throughput without changing the larger model's intended output quality.

Skill for Claude CodeCodex

About the project

synthetic-sciences/openscience is an AI workbench that carries out scientific research by reading papers, forming hypotheses, writing and running code, conducting experiments, analyzing results, and preparing reports. Researchers use it for work in machine learning, biology, physics, and chemistry with remote or local models. Catalogue add-ons extend its scientific workflows through skills and instructions.

synthetic-sciences/openscience · 3,473 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/synthetic-sciences/openscience/speculative-decoding
Any agent
npx skills add synthetic-sciences/openscience --skill speculative-decoding
Clone the repo
git clone --depth 1 https://github.com/synthetic-sciences/openscience

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for speculative-decoding

README.md
[![agentmods](https://agentmods.dev/badge/skills/synthetic-sciences/openscience/speculative-decoding.svg)](https://agentmods.dev/skills/synthetic-sciences/openscience/speculative-decoding)
Your own site
<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/speculative-decoding"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/speculative-decoding.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,759 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 98% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00077 $0.03759
Opus 5 $0.00039 $0.01879
Sonnet 5 $0.00015 $0.00752
Haiku 4.5 $0.00008 $0.00376

Measured yesterday against content hash 468651740332, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

speculative-decoding scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

98% identical to speculative-decoding — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

backend/cli/skills/ml-inference/speculative-decoding/SKILL.md · 469 lines

How it starts

The opening of the file, as written. The whole thing — 469 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Speculative Decoding: Accelerating LLM Inference

When to Use This Skill

Use Speculative Decoding when you need to:

  • Speed up inference by 1.5-3.6× without quality loss
  • Reduce latency for real-time applications (chatbots, code generation)
  • Optimize throughput for high-volume serving
  • Deploy efficiently on limited hardware
  • Generate faster without changing model architecture

Key Techniques: Draft model speculative decoding, Medusa (multiple heads), Lookahead Decoding (Jacobi iteration)

Papers: Medusa (arXiv 2401.10774), Lookahead Decoding (ICML 2024), Speculative Decoding Survey (ACL 2024)

Installation

# Standard speculative decoding (transformers)
pip install transformers accelerate

# Medusa (multiple decoding heads)
git clone https://github.com/FasterDecoding/Medusa
cd Medusa
pip install -e .

# Lookahead Decoding
git clone https://github.com/hao-ai-lab/LookaheadDecoding
cd LookaheadDecoding
pip install -e .

# Optional: vLLM with speculative decoding
pip install vllm

Quick Start

Basic Speculative Decoding (Draft Model)

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load target model (large, slow)
target_model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-2-70b-hf",
    device_map="auto",
    torch_dtype=torch.float16
)

# Load draft model (small, fast)
draft_model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-2-7b-hf",
    device_map="auto",
    torch_dtype=torch.float16
)

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-70b-hf")

# Generate with speculative decoding
prompt = "Explain quantum computing in simple terms:"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

# Transformers 4.36+ supports assisted generation
outputs = target_model.generate(
    **inputs,
    assistant_model=draft_model,  # Enable speculative decoding
    max_new_tokens=256,
    do_sample=True,
    temperature=0.7,
)

response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Read the full file on GitHub · 469 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 469 lines · 77 tokens per session scan A 468651740332

Subscribe to this mod's changes

speculative-decoding is a skill published in the GitHub repository synthetic-sciences/openscience (3,473 stars, last pushed today), licensed Apache-2.0. It adds 77 tokens to every session and 3,759 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to speculative-decoding, differing in 3 lines, and is treated as a copy.

Related

Other skills, from other repositories

speculative-decoding

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration…

davila7/claude-code-templates · 77 tokens

speculative-decoding

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration…

OpenLAIR/dr-claw · 77 tokens

speculative-decoding

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration…

Orchestra-Research/AI-Research-SKILLs · 77 tokens

speculative-decoding

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration…

liortesta/ClawdAgent · 77 tokens

speculative-decoding

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration…

OpenLAIR/dr-claw-plugin-cc · 77 tokens

speculative-decoding

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration…

ihatesea69/HieuNghi-AI-Skills · 77 tokens