home.social

#b300 — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #b300, aggregated by home.social.

fetched live
  1. Hacker News @[email protected] ·

    Running Kimi K3 on MI355X at Better Performance per Dollar Than B300

    wafer.ai/blog/kimi-k3-mi355x

    Comments: news.ycombinator.com/item?id=4

    #HackerNews #KimiK3 #MI355X #BetterPerformance #B300 #TechNews #AIHardware

    #hackernews #kimik3 #mi355x #betterperformance #b300 #technews
  2. deepseek @[email protected] ·
    ZFLOW AI improves B300 inference with simulation tuning Testing showed 826 tokens/second peak throughput and lower tail latency using disaggregated serving on DeepSeek V4-Pro. The post ZFLOW AI imp...

    #Industry #News #NVIDIA #B300 #platform #Simulation #ZFLOW #AI

    Origin | Interest | Match
    #industry #news #nvidia #b300 #platform #simulation
  3. Manc AvGeek @[email protected] ·

    Photo of the Day 16th March 2026.

    […]

    mancavgeek.co.uk/2026/03/16/ph

    #a320 #airbus #airfrance #airtours #avgeek #aviation
  4. Maquinari.cat @[email protected] ·

    Nvidia presenta Blackwell Ultra B300, 1.5X vegades més ràpid que el B200 i fins a 288GB de memòria HBM3e 🔥

    Això de la IA és un no parar.

    tomshardware.com/pc-components

    #Nvidia #B300 #B200 #IA #AI

    #nvidia #b300 #b200 #ia #ai
  5. HPC Guru @[email protected] ·

    Nvidia’s #B300 #GPU on the TSMC 4NP process node tweaked to deliver 50% higher FLOPS versus the B200 o 200W additional TDP o Upgrade to 12-Hi HBM3E from 8-Hi growing the HBM capacity per GPU to 288GB o Built For Reasoning Model Inference semianalysis.com/2024/12/25/n... #AI #HPC

    Nvidia’s Christmas Present: GB...

    #b300 #gpu #ai #hpc