hpcaitech / EnergonAILinks
Large-scale model inference.
☆629Updated last year
Alternatives and similar repositories for EnergonAI
Users that are interested in EnergonAI are comparing it to the libraries listed below
Sorting:
- Fast Inference Solutions for BLOOM☆564Updated 8 months ago
- Examples of training models with hybrid parallelism using ColossalAI☆340Updated 2 years ago
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆474Updated last year
- ☆411Updated last year
- Efficient Training (including pre-training and fine-tuning) for Big Models☆596Updated 3 weeks ago
- ☆543Updated 6 months ago
- Scalable PaLM implementation of PyTorch☆190Updated 2 years ago
- Microsoft Automatic Mixed Precision Library☆609Updated 8 months ago
- ☆219Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,397Updated last year
- PatrickStar enables Larger, Faster, Greener Pretrained Models for NLP and democratizes AI for everyone.☆761Updated 2 years ago
- LiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training☆406Updated last week
- Best practice for training LLaMA models in Megatron-LM☆656Updated last year
- Running BERT without Padding☆471Updated 3 years ago
- GPTQ inference Triton kernel☆302Updated 2 years ago
- Efficient AI Inference & Serving☆471Updated last year
- Official repository for LongChat and LongEval☆520Updated last year
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆692Updated 10 months ago
- Efficient Inference for Big Models☆584Updated 2 years ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,258Updated 3 months ago
- Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"☆295Updated 3 months ago
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,020Updated 2 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆845Updated 9 months ago
- Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.☆267Updated 2 years ago
- Serving multiple LoRA finetuned LLM as one☆1,066Updated last year
- Model Compression for Big Models☆162Updated last year
- ☆119Updated last year
- ☆127Updated 6 months ago
- LOMO: LOw-Memory Optimization☆987Updated 11 months ago
- Performance benchmarking with ColossalAI☆39Updated 2 years ago