Close Menu
techwavedispatch.com

    Subscribe to Updates

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

    What's Hot

    Nothing’s AI Device Debuts December 8, And It Looks Like Two Vapes Stuck Together

    November 20, 2026

    Why We Should Rethink the Sequential SFT-RL Paradigm

    November 20, 2026

    Chips can survive the space environment. Can their financing?

    November 20, 2026
    Facebook X (Twitter) Instagram
    Trending
    • Nothing’s AI Device Debuts December 8, And It Looks Like Two Vapes Stuck Together
    • Why We Should Rethink the Sequential SFT-RL Paradigm
    • Chips can survive the space environment. Can their financing?
    • Prescribed Bayesian Efficiency under Lifetime Adjustment Costs
    • Robot Videos: Morphing Robots, Dancing Humanoids, More
    • You Can Reveal The Full GTA 6 Map In Minutes Using This Simple Plane Trick
    • State-Space Compression for AI-Based Radio Resource Management of Vehicular Services
    • The 23 Best Early Black Friday Deals: Our Ultimate Picks (2026)
    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»Fast and Memory-Efficient Exact Sampling
    Machine Learning

    Fast and Memory-Efficient Exact Sampling

    adminBy adminNovember 17, 2026No Comments2 Mins Read
    Facebook Twitter Pinterest LinkedIn Tumblr Email
    Fast and Memory-Efficient Exact Sampling
    Share
    Facebook Twitter LinkedIn Pinterest Email

    [Submitted on 16 Mar 2026 (v1), last revised 12 Nov 2026 (this version, v4)]

    View a PDF of the paper titled FlashSampling: Fast and Memory-Efficient Exact Sampling, by Tomas Ruiz and 5 other authors

    View PDF
    HTML (experimental)

    Abstract:Sampling from a categorical distribution is mathematically simple, but in large-vocabulary decoding, it often triggers extra memory traffic and extra kernels after the LM head. We present FlashSampling, an exact sampling primitive that fuses sampling into the LM-head matmul and never materializes the logits tensor in HBM. The method is simple: compute logits tile-by-tile on chip, add Gumbel noise, keep only one maximizer per row and per vocabulary tile, and finish with a small reduction over tiles. In tensor-parallel decoding, FlashSampling replaces the all-gather of logits with streaming peer-to-peer writes: This overlaps GPU-to-GPU communication with computation and HBM loads across up to 8 GPUs, with near-ideal scaling at large batch sizes. Our kernel is exact because argmax decomposes over partitions; grouped variants for online and tensor-parallel settings are exact by hierarchical factorization of the categorical distribution. FlashSampling demonstrates kernel-level speedups on decode workloads across 4 different datacenter GPUs (H100, H200, B200, B300), and in end-to-end vLLM experiments, it reduces time per output token by up to $10%$ on the models we test. These results show that exact sampling, with no approximation, can be integrated into the matmul itself, consolidating the bandwidth-bound sampling step in an efficient epilogue.

    Submission history

    From: Yifan Zhang [view email]
    [v1]
    Mon, 16 Mar 2026 19:37:08 UTC (242 KB)
    [v2]
    Tue, 12 May 2026 21:02:06 UTC (252 KB)
    [v3]
    Fri, 25 Sep 2026 23:50:47 UTC (252 KB)
    [v4]
    Thu, 12 Nov 2026 22:27:21 UTC (260 KB)

    Exact Fast MemoryEfficient sampling
    Share. Facebook Twitter Pinterest LinkedIn Tumblr Email
    admin
    • Website

    Related Posts

    Why We Should Rethink the Sequential SFT-RL Paradigm

    November 20, 2026

    Prescribed Bayesian Efficiency under Lifetime Adjustment Costs

    November 20, 2026

    State-Space Compression for AI-Based Radio Resource Management of Vehicular Services

    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
    Gadgets & Smart Devices

    Nothing’s AI Device Debuts December 8, And It Looks Like Two Vapes Stuck Together

    By adminNovember 20, 20260

    Thanks, Swedish House Mafia. I guess.  Nothing In classic Carl Pei…

    Why We Should Rethink the Sequential SFT-RL Paradigm

    November 20, 2026

    Chips can survive the space environment. Can their financing?

    November 20, 2026

    Prescribed Bayesian Efficiency under Lifetime Adjustment Costs

    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

    Nothing’s AI Device Debuts December 8, And It Looks Like Two Vapes Stuck Together

    November 20, 2026

    Why We Should Rethink the Sequential SFT-RL Paradigm

    November 20, 2026

    Chips can survive the space environment. Can their financing?

    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

    Perplexity now has its own always-on AI agent

    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.