Saksham Arora — Chimera

Tag: Latency

4 items with this tag.

  • Aug 26, 2026

    OpenAI's First Chip Wins on Latency, Not FLOPs

    • Systems
    • Hardware
    • Inference
    • Latency
  • Aug 24, 2026

    JIT Compiling in 5 Microseconds, and Why That Number Sounded Familiar

    • Systems
    • Performance
    • Compilers
    • Latency
  • Aug 20, 2026

    Cerebras CS-4 Shipped a 2 Microsecond Interconnect, and That's the Number That Matters

    • Systems
    • Hardware
    • Inference
    • Latency
  • Jun 18, 2026

    The Average Latency Lie: What 100 LLM API Calls Taught Me About Benchmarking

    • LLM
    • Benchmarking
    • Latency
    • Systems
    • AI

  • GitHub
  • LinkedIn
  • Portfolio