hpcaitech / EnergonAILinks
Large-scale model inference.
☆629Updated 2 years ago
Alternatives and similar repositories for EnergonAI
Users that are interested in EnergonAI are comparing it to the libraries listed below
Sorting:
- ☆413Updated 2 years ago
- Fast Inference Solutions for BLOOM☆565Updated last year
- Examples of training models with hybrid parallelism using ColossalAI☆339Updated 2 years ago
- ☆547Updated 10 months ago
- ☆219Updated 2 years ago
- Microsoft Automatic Mixed Precision Library☆627Updated last year
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆479Updated last year
- LiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training☆407Updated 3 months ago
- PatrickStar enables Larger, Faster, Greener Pretrained Models for NLP and democratizes AI for everyone.☆768Updated 2 years ago
- Efficient AI Inference & Serving☆477Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,427Updated last year
- GPTQ inference Triton kernel☆313Updated 2 years ago
- Efficient Training (including pre-training and fine-tuning) for Big Models☆613Updated 2 weeks ago
- A high-performance inference system for large language models, designed for production environments.☆482Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,073Updated 4 months ago
- Running BERT without Padding☆475Updated 3 years ago
- Official repository for LongChat and LongEval☆531Updated last year
- Best practice for training LLaMA models in Megatron-LM☆659Updated last year
- Transformer related optimization, including BERT, GPT☆39Updated 2 years ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,297Updated 8 months ago
- Efficient Inference for Big Models☆587Updated 2 years ago
- Serving multiple LoRA finetuned LLM as one☆1,114Updated last year
- Scalable PaLM implementation of PyTorch☆188Updated 2 years ago
- ☆129Updated 10 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆924Updated last year
- Transformer related optimization, including BERT, GPT☆59Updated 2 years ago
- Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.☆1,006Updated last year
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆704Updated last year
- LLaMa/RWKV onnx models, quantization and testcase☆367Updated 2 years ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,217Updated last year