Surpassing vLLM with a Generated Inference Stack (infinity.inc) | HN Screenshots

YHacker Newsscreenshots

Screenshot of infinity.inc: Surpassing vLLM with a Generated Inference Stack

First screen, captured 7 months ago.

Looks similar

Screenshot of blog.kog.ai: Real-time LLM Inference on Standard GPUs: 3k tokens/s per request

Real-time LLM Inference on Standard GPUs: 3k tokens/s per request (blog.kog.ai)

189 points by NicoConstant 5 months ago | 88 comments

Screenshot of nuenki.app: Experimentation Matters: Why Nuenki isn't using pairwise evaluations

Experimentation Matters: Why Nuenki isn't using pairwise evaluations (nuenki.app)

4 points by Alex-Programs 1 year ago | 0 comments

Screenshot of devashish.me: Two Qwen3 models on one DGX Spark: the residency math

Two Qwen3 models on one DGX Spark: the residency math (devashish.me)

80 points by devashish86 4 months ago | 36 comments

Screenshot of myhsu.xyz: Scheduling Model in LLVM – Part I

Scheduling Model in LLVM – Part I (myhsu.xyz)

25 points by luu 2 years ago | 1 comments

Screenshot of myhsu.xyz: Scheduling Model in LLVM

Scheduling Model in LLVM (myhsu.xyz)

63 points by mshockwave 2 years ago | 2 comments

Screenshot of lamini.ai: Launch Lamini: The LLM Engine for Rapidly Customizing Models as Good as ChatGPT

Launch Lamini: The LLM Engine for Rapidly Customizing Models as Good as ChatGPT (lamini.ai)

103 points by sharonzhou 3 years ago | 40 comments