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
ClawBench
ClawBench
Bifrost
Bifrost
Busbar
Busbar

SalesforceAIResearch/Random-Attention

Code for the paper "Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning" https://arxiv.org/abs/2609.03430

Visit GitHub
Python
73
9
2 contributors
Apache License 2.0
website
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

Busbar

Control what AI can do before it acts

Momentum

How fast SalesforceAIResearch/Random-Attention 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

Sep 3 – Oct 22, 2026

Stars +48 in 50 days

0510
10

Forks +9 in 50 days

01
1

Merged PRs 0 in 50 days

01

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

Not in the Trendshift top 25 in this period

Sep 3Sep 10Sep 17Sep 24Oct 1Oct 8Oct 15Oct 22
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
Thu, Sep 3, 2026+0+00
Fri, Sep 4, 2026+0+00
Sat, Sep 5, 2026+6+00
Sun, Sep 6, 2026+1+10
Mon, Sep 7, 2026+10+10
Tue, Sep 8, 2026+10+00
Wed, Sep 9, 2026+2+10
Thu, Sep 10, 2026+3+10
Fri, Sep 11, 2026+1+10
Sat, Sep 12, 2026+0+00
Sun, Sep 13, 2026+2+10
Mon, Sep 14, 2026+3+00
Tue, Sep 15, 2026+2+00
Wed, Sep 16, 2026+0+00
Thu, Sep 17, 2026+0+00
Fri, Sep 18, 2026+1+00
Sat, Sep 19, 2026+0+00
Sun, Sep 20, 2026+1+00
Mon, Sep 21, 2026+1+10
Tue, Sep 22, 2026+1+00
Wed, Sep 23, 2026+0+00
Thu, Sep 24, 2026+1+00
Fri, Sep 25, 2026+0+00
Sat, Sep 26, 2026+0+00
Sun, Sep 27, 2026+0+00
Mon, Sep 28, 2026+0+10
Tue, Sep 29, 2026+0+00
Wed, Sep 30, 2026+1+10
Thu, Oct 1, 2026+0+00
Fri, Oct 2, 2026+0+00
Sat, Oct 3, 2026+0+00
Sun, Oct 4, 2026+0+00
Mon, Oct 5, 2026+0+00
Tue, Oct 6, 2026+0+00
Wed, Oct 7, 2026+0+00
Thu, Oct 8, 2026+1+00
Fri, Oct 9, 2026+0+00
Sat, Oct 10, 2026+0+00
Sun, Oct 11, 2026+0+00
Mon, Oct 12, 2026+0+00
Tue, Oct 13, 2026+0+00
Wed, Oct 14, 2026+0+00
Thu, Oct 15, 2026+0+00
Fri, Oct 16, 2026+0+00
Sat, Oct 17, 2026+1+00
Sun, Oct 18, 2026+0+00
Mon, Oct 19, 2026+0+00
Tue, Oct 20, 2026+0+00
Wed, Oct 21, 2026+0+00
Thu, Oct 22, 2026+0+00
Total+48+90
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Sep 91 post

    • 📄 Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning by Heng Wang, Jielin Qiu (@_Jason_Q) et al. Pins the prompt and randomly keeps non-prompt KV entries per head, replacing…

      Read full on X, posted by @papersdatacode

      @papersdatacode · x.com

  2. Sep 51 post

    • Random Attention: KV cache eviction without scoring Salesforce AI Research shows that keeping the prompt and evicting tokens uniformly at random per head matches learned evictors on reasoning tasks,…

      Read full on X, posted by @HuggingPapers

      @HuggingPapers · x.com

  3. Sep 41 post

    • Keep a reasoning model's prompt, then delete its own chain of thought at random, and it answers as accurately as it does under the most carefully tuned scheme for deciding which tokens to keep.…

      Read full on X, posted by @GptMaestro

      @GptMaestro · x.com

You might also like

Repositories close to SalesforceAIResearch/Random-Attention
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

Busbar

Control what AI can do before it acts

Zefan-Cai/R-KV

Python

[Neurips 2025] R-KV: Redundancy-aware KV Cache Compression for Reasoning Models

1.2k196

Zefan-Cai/KVCache-Factory

Python

Unified KV Cache Compression Methods for Auto-Regressive Models

1.4k178

WeianMao/triattention

Python

TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained GPUs.

86284

THUDM/IndexCache

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

14511

October2001/Awesome-KV-Cache-Compression

📰 Must-read papers on KV Cache Compression (constantly updating 🤗).

74830

SJTU-Storage-Lab/CacheSlide

Python
426352

Wenyueh/MinivLLM

Python

Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation

1.1k186

0xSero/turboquant

Python

TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration

1.8k205

microsoft/vattention

C

Dynamic Memory Management for Serving LLMs without PagedAttention

52644