Skip to content
View adcostanza's full-sized avatar
2 followers · 2 following

Achievements

Achievement: Arctic Code Vault ContributorAchievement: Pull Sharkx2

Achievements

Achievement: Arctic Code Vault ContributorAchievement: Pull Sharkx2

Block or report adcostanza

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
adcostanza/README.md

I write about running LLMs locally at acostanza.com.

  • benchmarks: SGLang serving speed and tool-calling benchmarks for Qwen3.8-27B, with configs, raw results and rerun commands
  • omp-plugins: extensions and skills for omp (oh-my-pi)

Pinned Loading

  1. benchmarks benchmarks Public

    Reproducible LLM inference benchmarks (SGLang serving speed, BFCL tool calling) behind the posts on acostanza.com

    Python

  2. omp-plugins omp-plugins Public

    Extensions and skills for omp (oh-my-pi), installable as a marketplace: omp plugin marketplace add adcostanza/omp-plugins

    TypeScript