Flash Attention: Fast and Memory-Efficient Exact Attention
12 similar packages · ranked by shared classifiers & health score · View flash-attn →
Causal depthwise conv1d in CUDA, with a PyTorch interface
File-based locks for Python on Linux and Windows
Optimizing compiler for evaluating mathematical expressions on CPUs and GPUs.
Optimizing compiler for evaluating mathematical expressions on CPUs and GPUs.
Manipulation and analysis of geometric objects
Fundamental algorithms for scientific computing in Python
A library for defining, optimizing, and efficiently evaluating mathematical expressions involving multi-dimensional arrays.
Cryptographic library for Python
Miscellaneous tools for scientific computing.
Cryptographic library for Python
Manhole is in-process service that will accept unix domain socket connections and present thestacktraces for all threads and an interactive prompt.
High level SSH command execution