Close Menu
techwavedispatch.com

    Subscribe to Updates

    Get the latest creative news from FooBar about art, design and business.

    What's Hot

    Exact Global-KV Memory Savings in a Paged Serving Engine with Unchanged Attention Kernels

    November 20, 2026

    YouTube is reportedly preparing to settle social media addiction claims for $3 billion

    November 20, 2026

    GTA 6 Made $3.79 Billion In Its First Day, But Rockstar’s Workers Still Lack Job Security

    November 20, 2026
    Facebook X (Twitter) Instagram
    Trending
    • Exact Global-KV Memory Savings in a Paged Serving Engine with Unchanged Attention Kernels
    • YouTube is reportedly preparing to settle social media addiction claims for $3 billion
    • GTA 6 Made $3.79 Billion In Its First Day, But Rockstar’s Workers Still Lack Job Security
    • Antom 3-in-1 Transformer: A Payment Foundation Model
    • A leaky AI supply chain is exposing secret user data at an alarming rate
    • Forecasting LLM Activations Before the First Answer Token
    • Astronomers watched a star spiral to its death inside a giant companion
    • OpenAI makes it much harder for attackers to extract how its latest AI models think
    Facebook X (Twitter) Instagram
    techwavedispatch.com
    Subscribe
    Friday, November 20
    • Home
    • AI Tools & Software
    • Machine Learning
    • Generative AI
    • Robotics & Automation
    • Future Tech & Hardware
    • AI in Business
    • Ethics & Regulations
    • More
      • Gadgets & Smart Devices
      • Cybersecurity & AI
      • Tech Breakthroughs
    techwavedispatch.com
    Home»Machine Learning»Exact Global-KV Memory Savings in a Paged Serving Engine with Unchanged Attention Kernels
    Machine Learning

    Exact Global-KV Memory Savings in a Paged Serving Engine with Unchanged Attention Kernels

    adminBy adminNovember 20, 2026No Comments2 Mins Read
    Facebook Twitter Pinterest LinkedIn Tumblr Email
    Exact Global-KV Memory Savings in a Paged Serving Engine with Unchanged Attention Kernels
    Share
    Facebook Twitter LinkedIn Pinterest Email

    [Submitted on 17 Nov 2026 (v1), last revised 19 Nov 2026 (this version, v2)]

    View a PDF of the paper titled Storing the Gemma 4 K=V Cache Once: Exact Global-KV Memory Savings in a Paged Serving Engine with Unchanged Attention Kernels, by Kushagra Bainsla

    View PDF
    HTML (experimental)

    Abstract:In the global attention layers of Gemma 4 31B, the value is the normalized key projection, and the key is the value scaled by a fixed weight, with rotary position encoding on one quarter of its dimensions. The Gemma 4 report states that this design reduces the global KV cache by up to 37.5%, but the open serving engines that we checked still store a full key and a full value: 1,024 values per KV head and token. We store one 640-value row instead, exact in real arithmetic, and an unchanged paged attention kernel reads it through two overlapping strided views as its key cache and its value cache. In a vLLM prototype with the 16-bit 31B model, the outputs are bit-identical to an emulation of the same arithmetic on the stock cache, 2 of 432 final answers differ from the stock engine (within its run-to-run noise), and the steady decode KV memory per request falls by a factor of 1.34 to 1.40 at 32K to 64K tokens. On a prefill/decode pair of two A100 GPUs with NIXL transfer and CPU offload, a decode engine with a full 15 GiB pool ran 1.38 times the stock decode tokens per step for 16K-token prompts (repeated to 0.06%) and 1.24 times for 8K-token prompts; a model of the vLLM block pool predicted both ratios to within 1% (the engine was 0.7% to 0.9% higher) and matched the change between them. The eager decode throughput rose by 1.30 and 1.11 times, and on this path the compact engine gave the same output tokens as the emulation for 8 prompts at batch 1. The run-time prototype makes an eager step 4% to 9% slower at equal batch, and the method does not yet stack with an 8-bit KV cache at the default scale.

    Submission history

    From: Kushagra Bainsla [view email]
    [v1]
    Tue, 17 Nov 2026 16:36:28 UTC (78 KB)
    [v2]
    Thu, 19 Nov 2026 16:34:27 UTC (79 KB)

    Attention engine Exact GlobalKV Kernels Memory Paged Savings Serving Unchanged
    Share. Facebook Twitter Pinterest LinkedIn Tumblr Email
    admin
    • Website

    Related Posts

    Antom 3-in-1 Transformer: A Payment Foundation Model

    November 20, 2026

    Forecasting LLM Activations Before the First Answer Token

    November 20, 2026

    Protein Functional Semantic Alignment via Representation Rectification

    November 20, 2026
    Leave A Reply Cancel Reply

    Top Posts

    NVIDIA Is Investigating Reports That CEO Jensen Huang Was The Target Of Chinese Spy Efforts

    November 8, 202619 Views

    ADIndex: Layer-Adaptive Sparse Attention Indexing via Group-Level Distillation

    November 11, 20265 Views

    Anthropic releases new Mythos and Fable models amid RSI concerns

    November 9, 20265 Views

    If AGI is so close, why is everyone leaving? The neolabs and their bets

    November 6, 20265 Views
    Don't Miss
    Machine Learning

    Exact Global-KV Memory Savings in a Paged Serving Engine with Unchanged Attention Kernels

    By adminNovember 20, 20260

    [Submitted on 17 Nov 2026 (v1), last revised 19 Nov 2026 (this version, v2)] View…

    YouTube is reportedly preparing to settle social media addiction claims for $3 billion

    November 20, 2026

    GTA 6 Made $3.79 Billion In Its First Day, But Rockstar’s Workers Still Lack Job Security

    November 20, 2026

    Antom 3-in-1 Transformer: A Payment Foundation Model

    November 20, 2026
    About Us

    Welcome to TechWave Dispatch

    At TechWave Dispatch, we bring you the latest news, insights, and developments from the ever-evolving world of technology. Our mission is to keep readers informed about the innovations shaping our digital future.

    From artificial intelligence and machine learning to cybersecurity, robotics, smart devices, and groundbreaking technologies, we cover the topics that matter in today's fast-moving tech landscape.

    Our Picks

    Exact Global-KV Memory Savings in a Paged Serving Engine with Unchanged Attention Kernels

    November 20, 2026

    YouTube is reportedly preparing to settle social media addiction claims for $3 billion

    November 20, 2026

    GTA 6 Made $3.79 Billion In Its First Day, But Rockstar’s Workers Still Lack Job Security

    November 20, 2026
    Most Popular

    After blocking Muse, Amazon now lets users text Alexa to help them shop

    November 6, 20260 Views

    A controlled world for robot learning and evaluation

    November 6, 20260 Views

    Egyptian and Nigerian English join the Open ASR Leaderboard

    November 6, 20260 Views
    Facebook X (Twitter) Instagram Pinterest
    • Terms and Conditions
    • Privacy Policy
    • Contact Us
    • About Us
    © 2026 TechWave Dispatch. All Rights Reserved.

    Type above and press Enter to search. Press Esc to cancel.