AIPM package
@orchestra-research/speculative-decoding@1.0.0
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques.
Scanned · no issuesPins this version in aipm.package.json and aipm-lock.json.
aipm add @orchestra-research/speculative-decoding@1.0.0Writes the skill files only. Add --no-init to skip aipm.package.json and the lockfile.
aipm add @orchestra-research/speculative-decoding@1.0.0 --no-initInstall the skill above, then run this in your AI tool:
/speculative-decoding <your description>## When to Use This Skill
Source
Preview every file this package writes on install before you run the command above.
Loading package files…
Share this package
Add this badge to a GitHub README so readers can open the package page and install the same version.
[](https://www.aipm-registry.com/skills/orchestra-research/speculative-decoding/1.0.0?utm_source=github&utm_medium=readme&utm_campaign=package_badge)
Publisher
This imported publisher has not claimed its AIPM account. A connected account confirms account control, but it does not guarantee that a package is safe.
AI assistant context
@orchestra-research/speculative-decoding@1.0.0 is an AIPM skill package for All tools. Use it when a project needs the reusable AI behavior described as: 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...
Tool targets
Add --no-init to any of these when you want the skill files without aipm.package.json or aipm-lock.json.
Run this variant when you want to install the package into cursor.
aipm add @orchestra-research/speculative-decoding@1.0.0 --target cursor --ciRun this variant when you want to install the package into claude.
aipm add @orchestra-research/speculative-decoding@1.0.0 --target claude --ciKeep exploring
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast...
Published by Orchestra Research
Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform
Published by Orchestra Research
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...
Published by Orchestra Research
Package FAQ
AIPM skills can add files to your project. Review the package name, target, description, license, and publisher before installing. Use a clean branch when trying a new skill.
Discussion
Comments (0)
Sign in to leave a comment.
Loading comments…