No description available.
โญ Canonical โ this is the single source of truth for this project.
| Field | Value |
|---|---|
| Name | sd-llm-benchmark |
| Tier | ๐๏ธ Archive |
| Description | No description available. |
| Visibility | ๐ Private |
| Fork | No |
| Last activity | ย |
| Status | โ Archived |
| Original source | Github |
| Original owner | guneysus |
A benchmarking tool for evaluating Large Language Model (LLM) performance on structured data tasks, including GPU-accelerated inference.
"""
GPU Benchmarking Tool
This script benchmarks GPU performance for both:
1. Stable Diffusion image generation at specified resolutions and step counts
2. LLM inference speed in tokens per second
Usage:
python gpu_benchmark.py --gpu [gpu_name] [other options]
"""
import argparse
import json
import os
import time
import platform
import torch
import numpy as np
from datetime import datetime
from tqdm import tqdm
# For Stable Diffusion
try:
from diffusers import StableDiffusionPipeline
except ImportError:
repos/github.com/guneysus/sd-llm-benchmarkgit@github.com:guneysus/archive.gitgit@gitlab.com:guneysu/archive.gitgitea@192.168.1.19:guneysu.dev/github-archive.git| โ ramblings | _edit โ |
Generated by scripts/generate.py ยท Back to index