-
POSTECH (Pohang University of Science and Technology
- Pohang, Korea
-
12:02
(UTC +09:00) - @changhunlee_
Highlights
- Pro
Stars
A high-throughput and memory-efficient inference and serving engine for LLMs
Code for the AAAI 2024 Oral paper "OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models".
Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models" (ICLR 2024)
๐A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.
Awesome LLM compression research papers and tools.
๐ฏ Curated coding interview preparation materials for busy software engineers
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficieโฆ
Acceptance rates for the major AI conferences
The toolkit to test, validate, and evaluate your models and surface, curate, and prioritize the most valuable data for labeling.
Refine high-quality datasets and visual AI models
vitrun / FasterTransformer
Forked from NVIDIA/FasterTransformerTransformer related optimization, including BERT, GPT
A Gradio web UI for Large Language Models.
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
<โก๏ธ> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.
Source code for Twitter's Recommendation Algorithm
๐ ์ ์ ๊ฐ๋ฐ์๋ก์ ์ฑ์ฅ์ ์ํ ์ ๊ณต ์ง์์ ์ ๋ฆฌํฉ๋๋ค ๐
์ฝ๋ฉ ํ ์คํธ ๊ด๋ จ ๊ธฐ์ถ๋ฌธํญ์ ํ์ด๋ณด๊ณ ์์ค์ฝ๋ ๋ฐ ์ค๋ช ์ ์ ๋ก๋ํฉ๋๋ค.
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (Vโฆ
My continuously updated Machine Learning, Probabilistic Models and Deep Learning notes and demos (2000+ slides) ๆไธ้ดๆญๆดๆฐ็ๆบๅจๅญฆไน ๏ผๆฆ็ๆจกๅๅๆทฑๅบฆๅญฆไน ็่ฎฒไน(2000+้กต)ๅ่ง้ข้พๆฅ
Awesome Knowledge Distillation
Fast and accurate object detection with end-to-end GPU optimization
Color palettes which are also distinguishable when printed in grayscale
rickiepark / python-machine-learning-book-2nd-edition
Forked from rasbt/python-machine-learning-book-2nd-edition<๋จธ์ ๋ฌ๋ ๊ต๊ณผ์ with ํ์ด์ฌ, ์ฌ์ดํท๋ฐ, ํ ์ํ๋ก>์ ์ฝ๋ ์ ์ฅ์
Collection of recent methods on (deep) neural network compression and acceleration.
C++ based maze solver, accelerated with Nvidia CUDA
Command-line program to download videos from YouTube.com and other video sites