Skip to main content

Optimizer Agent

A library to auto optimize and discover things with an LLM agent.

Getting started:

  1. Installation
python3 -m venv env_optagent
source env_optagent/bin/activate

pip3 install -e .
  1. Running example:
# ./examples/test_example/run.sh
./examples/cuda_engineering/run.sh

# Run the model first
CUDA_VISIBLE_DEVICES=0 python3 -m sglang.launch_server \
--model-path Qwen/Qwen3-Coder-30B-A3B-Instruct \
--tensor-parallel-size 1 \
--host 0.0.0.0 \
--port 30000 \
--enable-memory-saver

Other useful commands:

salloc --partition=interactive-gpu --gres=gpu:h200:2 --time=02:00:00 --ntasks=1
srun --pty --overlap --jobid=120608 bash

source ~/miniconda3/etc/profile.d/conda.sh
conda activate env_model2 #sglang
conda activate env_kb2 #kb

(C) Nikolai Rozanov - 2026 - Present

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

optimizer_agent-0.0.0.1.tar.gz (47.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

optimizer_agent-0.0.0.1-py3-none-any.whl (38.8 kB view details)

Uploaded Python 3

File details

Details for the file optimizer_agent-0.0.0.1.tar.gz.

File metadata

  • Download URL: optimizer_agent-0.0.0.1.tar.gz
  • Upload date:
  • Size: 47.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.11.15

File hashes

Hashes for optimizer_agent-0.0.0.1.tar.gz
Algorithm Hash digest
SHA256 f2e8d3051ef1d49bbc6925789a10776db2f603ab4054ef92a72ecb49e031039a
MD5 98e4066707f989fd36f51172e007013e
BLAKE2b-256 ffe9accc3ae1c6ed48367e60b060bbaef88602529010f1f7d3a9c21cd631af44

See more details on using hashes here.

File details

Details for the file optimizer_agent-0.0.0.1-py3-none-any.whl.

File metadata

File hashes

Hashes for optimizer_agent-0.0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 d9f9247413ff52515c05256655f5853bdc08968fe7941fc24e38e982cdabd8a1
MD5 fb8815a85347b72c4373b25670a8d2bd
BLAKE2b-256 523c7a8d89139a30e37094267d86f23a3bde681045f4cdf3e6eb819856f88dd5

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page