AITeX★ 236⑂ 17 forksMIT
OpenMachine-ai/transformer-tricks
TRANSFORMER-TRICKS - ACCELERATING TRANSFORMERS
A collection of techniques and utilities for accelerating transformers: attention optimization, quantization, and caching of computations.
// KEY FEATURES
- Techniques for speeding up self‑attention without losing accuracy
- Methods for post‑training quantization of models
- Ready-to-use scripts for profiling and accelerating inference
#ai#arxiv#arxiv-papers#llm#llm-inference#llmops#machine-learning#python#transformer#transformer-models#transformer-pytorch
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram