b-albar

AI Engineer

CATIEFrance

Pinned Repositories

chessformer
Chessformer
Language:Rust0 0 00
flash-attention
Fast and memory-efficient exact attention
Language:Python00
flashT5
A fast implementation of T5/UL2 in PyTorch using Flash Attention
Language:Python00
portfolio
Personal Portfolio in Machine Learning
Language:HTML00
flashT5
A fast implementation of T5/UL2 in PyTorch using Flash Attention
Language:Python65 7 58
rustlm
RustLM : An efficient Rust CTC Decoder supporting external language models
Language:Rust0 1 00
triton-rust
An api for interfacing Nvidia Trition Inference Server with Rust
Language:Rust7 2 00
flash-attention
Fast and memory-efficient exact attention
Language:Python13.8k 115 1.1k1.3k
lightly
A python library for self-supervised learning on images.
Language:Python3.1k 29 568277
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Language:Python83.1k 1.7k 45.8k22.4k

b-albar's Repositories

b-albar/chessformer
Chessformer
Language:Rust0 0 00
b-albar/FlagAttention
A collection of memory efficient attention operators implemented in the Triton language.
Language:Python0 0 00
b-albar/portfolio
Personal Portfolio in Machine Learning
Language:HTML00
b-albar/rebased
Official implementation of the paper "Linear Transformers with Learnable Kernel Functions are Better In-Context Models"
Language:Python0 0 00