speculative-decoding SKILL.md skillA
speculative-decoding from orchestra-research/ai-research-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add orchestra-research/ai-research-skills/speculative-decoding@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- orchestra-research/ai-research-skills
- Path
19-emerging-techniques/speculative-decoding/SKILL.md- Versions recorded
- 5
- Latest version
- v1.0.0, committed Nov 20, 2025
- First version recorded
- Nov 19, 2025
- Size
- 14,072 bytes
- Repository stars
- 13,718
- License
- MIT
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, parallel token generation, and production deployment strategies.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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 ```bash # 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) ```python from transformers import AutoModelForCausalLM, AutoTokenizer …
Read the whole file at its exact version.
How to install
mdr add orchestra-research/ai-research-skills/speculative-decoding@sha256:d818b841ffe3e338The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_7jfq5zrlsst52cmk)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Nov 19, 2025 and Nov 20, 2025, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2025-11-20 | 0a9ded4 | 14,072 B | A | view · diff |
| v1.0.0 | 2025-11-20 | 51fc3a3 | 14,051 B | A | view · diff |
| v1.0.0 | 2025-11-20 | 81c38fe | 14,050 B | A | view · diff |
| v1.0.0 | 2025-11-19 | bd4461f | 14,049 B | A | view · diff |
| git:20251119.66e31d2 | 2025-11-19 | 66e31d2 | 13,791 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (14072 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
orchestra-research/ai-research-skills · 13,718 stars · license MIT · pushed 2026-10-11 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_7jfq5zrlsst52cmk GET https://markdownregistry.com/api/v1/resolve?ref=orchestra-research/ai-research-skills/speculative-decoding GET https://markdownregistry.com/api/v1/blob/d818b841ffe3e338569ab7caa0d54516f51c649e52fd1af2d5de5d0435b39f99
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.