deepseek-ai/DeepSpec

DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms

Language modelsPython

1.2 Steady Magnitude out of 10. Star growth looks organic. Data as of September 14, 2026.

About the project

Full-stack pipeline for training and evaluating draft models for speculative decoding: data preparation, training against a target-model cache, and acceptance measurement on benchmarks. Supports DSpark, DFlash and Eagle3.

Useful for

Train a draft model to speed up Qwen3-4B inference on a single 8-GPU node
Measure speculative-decoding acceptance on gsm8k and humaneval with a released checkpoint
Build a target cache from open-perfectblend to train a new draft model

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

5 stars today.
Top new repositories in the last 4 months: #61.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 7,115
Stars in a day: 5
Forks: 667
Issues and pull requests: 85
Watchers: 34
Language: Python
License: MIT
Created: June 26, 2026
Last push: July 9, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in

September 13, 2026Top new repositories in the last 4 months: #61

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/deepseek-ai/DeepSpec.svg?lang=en)](https://gitnova.dev/en/r/deepseek-ai/DeepSpec)

Similar projects

6.1
JustVugg/colibri
A pure-C, zero-dependency inference engine for running large MoE models (744B–2.8T parameters) on consumer hardware by treating VRAM, RAM, and storage as a single multitier hierarchy and streaming experts from disk.

BreakoutLanguage modelsC+1,048 stars in a day
5.7
asgeirtj/system_prompts_leaks
A collection of extracted system prompts from Anthropic, OpenAI, Google, xAI and others — the hidden instructions chatbots receive before a user's first message.

BreakoutLanguage modelsJavaScript+428 stars in a day
5.1
kennethwolters/litelm
A lightweight litellm alternative: routes LLM calls across 19 providers and translates message formats in ~2,900 lines with two dependencies, without proxy, caching, or cost tracking.

Early signalLanguage modelsPython+9 stars in a day
5.0
MiaAI-Lab/DeepSeek-v4.1-Flash-EXL3-2x-DGX-Sparks
A local EXL3 2.9 bpw checkpoint of DeepSeek-V4.1-Flash (196 GiB, 39 shards) served via an OpenAI-compatible vLLM API on a 2x NVIDIA GB10 (DGX Spark) kit with tensor-parallel 2. Includes DSpark speculative decoding and…

Early signalLanguage modelsPython+81 stars in a day
4.8
unclecode/crawl4ai
Open-source web crawler and scraper that turns pages into clean, LLM-ready Markdown for RAG, agents and data pipelines. Runs via Python API, CLI and Docker with no API keys.

BreakoutLanguage modelsPython+411 stars in a day
4.5
Edge0-AI/Edge0
An open-source streaming MoE inference framework: expert weights are offloaded from SSD on demand while a trained prerouter predicts routing ahead of time. Runs on Apple Silicon via MLX and ships with two ready-to-run…

CoolingLanguage modelsPython+118 stars in a day