1 repo
Awesome GitHub RepositoriesEfficient Inference Engines
Runtime environments and libraries optimized for executing large language models with minimal latency and memory usage.
Distinguishing note: Focuses on the engine-level execution of compressed models rather than model training or fine-tuning.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Efficient Inference Engines. Refine with filters or upvote what's useful.
Awesome Efficient Inference Engines GitHub Repositories
Find the best repos with AI.We'll search the best matching repositories with AI.
- microsoft/BitNet
microsoft/BitNet
28,521View on GitHubBitNet is a quantized inference engine designed to execute highly compressed language models by performing arithmetic on low-precision, bit-level weight data. It functions as a model optimization toolkit and a high-performance kernel library, enabling the execution of large language models on consumer hardware by reducing memory footprints and increasing processing speeds. The project distinguishes itself through hardware-specific kernel optimizations that leverage native processor instructions to accelerate matrix multiplication. By utilizing packed integer arithmetic and memory-aligned weig
Running compressed language models on consumer hardware by reducing memory usage and increasing processing speed during text generation.
Python
