VOOZH about

URL: https://www.together.ai/mlsys-2026

⇱ Meet us at MLSys 2026 | Together AI


Events / MLSys 2026
Platinum Sponsor

Together AI at MLSys 2026

  • May 18-22, 2026
  • Bellevue, WA
Time to start

00

Days

:

Days

00

Hours

:

Days

00

Minutes

:

Days

00

Seconds
πŸ‘ Image
πŸ‘ Image
platinum Sponsor

Join us at MLSys

Where the world’s deep learning community comes to build what’s next: Accelerated compute, production inference, model shaping, and research β€” all at the frontier of AI.

Join us for an exclusive event

Come unwind after a day at MLSys with drinks, after party bites, shuffleboard, and even better company.
Join fellow researchers and builders shaping what’s next in AI.

Papers we’re presenting at MLSys

  • research paper
    FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling
    • may 21
    • 6 p.m.
    Ted Zadouri
    Markus Hoehnerbach
    Jay Shah
    Timmy Liu
    Vijay Thakkar
    Tri Dao
  • research paper
    ParallelKittens: Systematic and Practical Simplification of Multi-GPU AI Kernels
    • may 21
    • 4:30 p.m.
    Stuart H. Sul
    Simran Arora
    Benjamin Spector
    Christopher RΓ©
  • research paper
    Beat the long tail: Distribution-Aware Speculative Decoding for RL Training
    • may 20
    • 4 p.m.
    Zelei Shao
    Vikranth Srivatsa
    Sanjana Srivastava
    Qingyang Wu
    Shirley Wu
    Shirley Wu
    Ameen Patel
    Jue Wang
    Percy Liang
    Tri Dao
    Ce Zhang
    Yiying Zhang
    Ben Athiwaratkun
    Chengfeng Xu
    Junxiong Wang
  • research paper
    Search Your NVFP4 Scales!
    • may 20
    • 5:30 p.m.
    Tanmaey Gupta
    Hayden Prairie
    Hayden Prairie
    Reyna Abhyankar
    Qingyang Wu
    Austin Silveria
    Pragaash Ponnusamy
    Jue Wang
    Ben Athiwaratkun
    Leon Song
    Tri Dao
    Daniel Fu
    Christopher De Sa
  • research paper
    CDLM: Consistency Diffusion Language Models for faster sampling
    • may 21
    • 8:45 A.m.
    Minseo Kim
    Chenfeng Xu
    Coleman Hooper
    Harman Singh
    Ben Athiwaratkun
    Ce Zhang
    Kurt Keutzer
    Amir Gholami
  • research paper
    OSWorld-Human: Benchmarking the Efficiency of Computer-Use Agents
    • may 19
    • 1:00 p.m.
    Reyna Abhyankar
    Qi Qi
    Yiying Zhang
  • research paper
    Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost
    • may 20
    • 2:15 p.m.
    Haojun Xia
    Shirley Wu
    Jisen Li
    Tsai-chuan Wu
    Junxiong Wang
    Jue Wang
    Chenxi Li
    Aman Singhal
    Alay Dilipbhai Shah
    Donglin Zhuang
    Zhongzhu Zhou
    Ben Athiwaratkun
    Zhen Zhang
    Leon Song

We’re hiring

Whether you're a developer, researcher, or enthusiast, there's a place for you in Together AI.

πŸ‘ Image

Meet the Together AI team

Say hello to the researchers turning ideas into production on the AI Native Cloud.