Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats

Bifrost
Bifrost
ClawBench
ClawBench

ZinYY/AdaFlash

[COLMW'26 Spotlight] AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters

Visit GitHub
Python
134
20
1 contributors
website
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

ClawBench

a benchmark for personal agents

Momentum

How fast ZinYY/AdaFlash is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Oct 17 – Oct 24, 2026

Stars +6 in 8 days

0123
3

Forks +0 in 8 days

01

Merged PRs 0 in 8 days

01

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Oct 17Oct 18Oct 19Oct 20Oct 21Oct 22Oct 23Oct 24
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Sat, Oct 17, 2026+0+00
Sun, Oct 18, 2026+1+00
Mon, Oct 19, 2026+3+00
Tue, Oct 20, 2026+1+00
Wed, Oct 21, 2026+1+00
Thu, Oct 22, 2026+0+00
Fri, Oct 23, 2026+0+00
Sat, Oct 24, 2026+0+00
Total+6+00
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Oct 181 post
    • 扩散草稿模型把并行生成的成本降了下来,却也把“什么时候该相信草稿、验证多少 Token”变成了部署问题。AdaFlash 给出的答案是:让模型从每次验证中学习,并让验证长度随草稿质量和系统负载变化。 当大模型开始被 Agent 高频调用,推理加速的关键不再只是一次前向传播能生成多少 Token,还包括系统能否在真实流量中持续识别并跳过无效计算。AdaFlash…

      Read full on X, posted by @qingke_ai

      @qingke_ai · x.com

You might also like

Repositories close to ZinYY/AdaFlash
FeaturedAdvertise to 180K+ monthly visitors
ClawBench

a benchmark for personal agents

Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

z-lab/dflash

Python

DFlash: Block Diffusion for Flash Speculative Decoding

6.2k475

deepseek-ai/DeepSpec

Python

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

7.2k713

fvliang/DART

Python

Official Implementation of DART (DART: Low-Latency Parallel Drafting with Continuity-Aware Tree Pruning for Speculative Decoding, EMNLP26).

723

hao-ai-lab/JetSpec

Python

JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Causal Parallel Tree Drafting

24116

jianuo-huang/Domino

Python

[EMNLP2026 Main] Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.

1397

SafeAILab/EAGLE

Python

Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).

2.6k294

vllm-project/speculators

Python

A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM

920282

chiennv2000/orthrus

Python

[NeurIPS 2026 Spotlight] Fast, lossless LLM inference via dual-view diffusion decoding.

48225

ifm-ai/uno

Python

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

10717