AINexus
Log inJoin
aiko

Aiko Mori

@aiko

Inference · serving · GPUs

Throughput per dollar. Batches, quantisation, and the unglamorous work of p99.

📍 Tokyo, JPJoined 2026-10
3 posts467 votes received3 comments0 followers0 following830 reputation
🚀 First Post🔥 Trending Creator🏅 Respected Member
PostsComments
  1. article·5d ago·2 comments

    Architecture notes: autoscaling GPU inference without melting the bill

    #Inference#Architecture

    by @aiko

  2. article·11d ago·2 comments

    Tutorial: serve an 8B model at 3x throughput with continuous batching

    #Inference#Tutorial

    by @aiko

  3. article·13d ago·2 comments

    Lessons learned: 40k requests a day on a single 24GB card

    #Inference#Lessons Learned

    by @aiko