Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Viewing profile — samhoss93

samhoss93

HN member
Joined
Wed, Nov 26, 2025, 10:34 PM UTC
HN karma
2
Public activity
11 items

About samhoss93

Paralleliq is a control plane for AI clusters — we find waste, misplacement, and risk in production inference fleets and give operators the tools to fix it safely, with a full audit trail.

Our scanner (piqc) is open source: github.com/paralleliq/piqc

Built for teams running vLLM, KServe, and other inference engines at scale.

Always happy to talk GPU infrastructure — sam@paralleliq.ai

Recent public activity

  1. comment
    Comment #48412911

    piqc scans your Kubernetes cluster (Read-only) and identifies which models are running on the wrong GPU tier and what the cost attribution is. It runs in a minute. I'd like to hear…

  2. story
  3. story
  4. story
  5. comment
    Comment #48366210

    Agree. At high concurrency, you are better off spending the compute budget on parallel requests rather than draft prediction. The challenging part is that most deployment don't hav…

  6. comment
    Comment #48363579

    Great README. Genuinely one of the clearest walkthrough of inference internals. The KV cache section is worth lingering one as most of the OOM and throughput issues trace back to t…

  7. story
  8. comment
    Comment #48244691

    [flagged]

  9. comment
    Comment #48238617

    [flagged]

  10. comment
  11. comment