Beast code in Giters

SeunghyunHan's starred repositories

LLM training in simple, raw C/CUDA

Language:CudaMIT2013600

Fast and memory-efficient exact attention

Language:PythonBSD-3-Clause1137800

A high-throughput and memory-efficient inference and serving engine for LLMs

Language:PythonApache-2.02033200

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

Language:PythonApache-2.0175200

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

Language:PythonApache-2.038400

SPLADE: sparse neural search (SIGIR21, SIGIR22)

Language:PythonNOASSERTION66900

A curated list of awesome papers for Semantic Retrieval (TOIS Accepted: Semantic Models for the First-stage Retrieval: A Comprehensive Review).

Get daily arxiv notification with pre-defined keywords

Language:Python6600

Solutions for Leetcode problems

Language:Java700

Implementation of "Use of Deep Learning for Characterization of Microfluidic Soft Sensors" (RA-L and ICRA'2018)

Language:Python800

Kakao Arena 2nd Competition - "Article recommendations for Brunch Users"

Language:Python600

A TensorFlow Implementation of Convolutional Sequence Embedding Recommendation Model (Caser)

Language:Python1300

Comparison of famous convolutional neural network models

MIT32100