PulseAugur / Brief
EN
LIVE 01:48:46

Brief

last 24h
[1/1] 221 sources

Multi-source AI news clustered, deduplicated, and scored 0–100 across authority, cluster strength, headline signal, and time decay.

  1. I built a Mamba1 variant I call SM1 with d_state=1 that runs on Blackwell in pure PyTorch [P]

    A developer has created SM1, a variant of the Mamba1 architecture, optimized for PyTorch and capable of running on NVIDIA Blackwell hardware. SM1 replaces the selective scan with two native PyTorch operations, achieving the exact closed-form solution for the d_state=1 recurrence. This optimization significantly reduces memory usage, with a 130M parameter model requiring only 56 KB for its inference state, eliminating the need for a KV cache. AI

    IMPACT This optimized Mamba variant could lead to more efficient training and inference for certain sequence modeling tasks.