Flash Attention CUTE (CUDA Template Engine) implementation
12 similar packages · ranked by shared classifiers & health score · View flash-attn-4 →
Generic application schema implemented in python
A minimal low-level HTTP client.
A collection of accessible pygments styles
Wrapper around elasticsearch-dsl-py for django models
Create computational narratives that are reusable, reproducible, and interactive.
plugable dependency injection and result processing
S-expression parser for Python
Validate STIX 2 Patterns.
A stub emulator for the Google Cloud Storage API
Django components that know how to render themselves.
Functions to manipulate batches of PyTorch tensors
Elegant HTTP Caching for Python