Latest News for: fp8

Edit

Tenstorrent Enables AI At Scale with Industry-Leading Performance Deployed on Novel Networked AI Architecture

ACCESSWIRE 28 Apr 2026
Blitz Mode ... Decode ... Starting at $110,000, it delivers 23 PFLOPS Block FP8 of AI compute from 32 Blackhole chips, 6.2 GB of on-chip SRAM with 2.9 PB/s, 1 TB of DRAM with 16 TB/s, and up to 56 � 800G Ethernet ports for 11.2 GB/s of scale-out bandwidth.
Edit

NVIDIA NeMo RL Achieves 48% Speedup with End-to-End FP8 Precision Training

BitRSS 21 Apr 2026
NVIDIA's new FP8 recipe for reinforcement learning delivers 48% faster training while matching BF16 accuracy, cutting AI infrastructure costs significantly. (Read More) ... .
  • 1
×