snowflake-arctic

LLM inference stack

A project providing optimized stacks for fine-tuning and inference of large language models, focusing on low-latency and high-throughput performance.

GitHub

525 stars
6 watching
47 forks
Language: Python
last commit: 5 months ago

Related projects:

Repository Description Stars
pratyushmaini/llm_dataset_inference Detects whether a given text sequence is part of the training data used to train a large language model. 23
deepseek-ai/deepseek-moe A large language model with improved efficiency and performance compared to similar models 1,024
ediglacuq/fenics_ice A framework for Bayesian quantification of uncertainty in large-scale ice sheet models. 5
luogen1996/lavin An open-source implementation of a vision-language instructed large language model 513
mlcommons/inference Measures the performance of deep learning models in various deployment scenarios. 1,256
gmftbygmftby/science-llm A large-scale language model for scientific domain training on redpajama arXiv split 125
nixtla/mlforecast A framework to perform time series forecasting using machine learning models on large datasets. 924
dreadnode/rigging A framework for leveraging language models in production code 216
damo-nlp-sg/m3exam A benchmark for evaluating large language models in multiple languages and formats 93
talwalkarlab/leaf A benchmarking framework for federated machine learning tasks across various domains and datasets 856
kvcache-ai/ktransformers A flexible framework for LLM inference optimizations with support for multiple models and architectures 771
davidmigloz/langchain_dart Provides a set of tools and components to simplify the integration of Large Language Models into Dart/Flutter applications 441
snunez1/llama.cl A Common Lisp port of a Large Language Model (LLM) implementation 36
microsoft/msrflute A platform for conducting high-performance federated learning simulations in Python. 185
clue-ai/promptclue A pre-trained language model for multiple natural language processing tasks with support for few-shot learning and transfer learning. 656