DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
machine-learningpytorchdeep-learninginferencemixture-of-expertsgputrillion-parameterszerobillion-parameterscompressiondata-parallelismmodel-parallelismpipeline-parallelism- Python
01Обновлено 7 месяцев назад
Making large AI models cheaper, faster and more accessible
aideep-learninginferencefoundation-modelsmodel-parallelismpipeline-parallelismdata-parallelismbig-modeldistributed-computingheterogeneous-traininghpclarge-scale- Python
01Обновлено 7 месяцев назад
🤗 Optimum Intel: Accelerate inference with Intel optimization tools
- Python
00Обновлено 7 месяцев назад
A high-throughput and memory-efficient inference and serving engine for LLMs
- Python
00Обновлено 8 месяцев назад
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
- Python
00Обновлено 7 месяцев назад
ncnn is a high-performance neural network inference framework optimized for the mobile platform
deep-learningpytorchartificial-intelligenceandroidinferenceiosneural-networkvulkantensorflowkerasonnxriscvcaffemxnetncnnsimdarm-neondarknethigh-preformancemlir- C++
00Обновлено месяц назад
Large Language Model Text Generation Inference
- Python
00Обновлено 7 месяцев назад