inclusionAI/ASpec
Library
Can I trust it?
Worth a closer look before you use it.
Warnings Check
Very new: it was created 2 days ago. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change today.
Licence OK
Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
A high-throughput training framework for speculative decoding draft models. It optimizes draft forward and backward passes, overlaps training with target feature generation, and shares compatible target features across independent draft experiments.
Who it's for
ML engineers training speculative decoding draft models (DSpark, DFlash, EAGLE3) for large language models on multi-GPU setups
How to use it
Install
bash setup.shFrom its README. Check it there before running it.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up inclusionAI/ASpec in my project. Follow its README: https://github.com/inclusionAI/ASpec. Explain each step and check it is safe before running anything.
Star curve
Alternatives
Similar projects named in its profile. Each link searches the directory.
Get alerts for repos like this
We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/inclusionAI/ASpec?ref=badge)Similar repos
- eagle-hq/EAGLE-4
Official inference code for EAGLE-4, a speculative decoding system whose drafter adapts its speculation to batch size, hardware and workload. It serves EAGLE-4 drafts on SGLang, vLLM and TokenSpeed th
- StargazerX0/SpecPilot
Agentic loop that discovers lossless optimizations for speculative decoding, shipping tuned serving engines for six deployments of Qwen3.8-27B and Muse-Glimmer-30B with DFlash2 and DSpark drafters on
- prabanta-dev/janas
A C inference engine for running large mixture-of-experts language models on ordinary computers, with or without a GPU. Weights stay on disk, and the experts each token needs are streamed from an NVMe
- deepseek-ai/DeepInfer
Inference framework for serving DeepSeek models at scale, released as an offline inference build. Provides optimized kernels, attention and MoE parallelism, speculative decoding, asynchronous scheduli
- HazyResearch/ncm
Research code for Next-Concept Modeling, a two-stage framework for parallel text generation. A multiscale residual VQ tokenizer maps sequences to hierarchical discrete codes, and a transformer predict
- simplexai-labs/PolyStrata
Runs large open-weight language models locally on an NVIDIA GPU, with OpenAI- and Anthropic-compatible API endpoints served on localhost. Includes a second, experimental inference engine for several m