laekov / fastmoeLinks
A fast MoE impl for PyTorch
☆1,734Updated 3 months ago
Alternatives and similar repositories for fastmoe
Users that are interested in fastmoe are comparing it to the libraries listed below
Sorting:
- Tutel MoE: Optimized Mixture-of-Experts Library, Support DeepSeek FP8/FP4☆824Updated this week
- PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538☆1,111Updated last year
- A curated reading list of research in Mixture-of-Experts(MoE).☆625Updated 7 months ago
- A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models☆758Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆2,081Updated 2 months ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,391Updated last year
- A collection of AWESOME things about mixture-of-experts☆1,135Updated 5 months ago
- Rotary Transformer☆959Updated 3 years ago
- ☆638Updated last week
- PyTorch extensions for high performance and large scale training.☆3,322Updated last month
- Pytorch library for fast transformer implementations☆1,710Updated 2 years ago
- Best practice for training LLaMA models in Megatron-LM☆654Updated last year
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,417Updated 10 months ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,435Updated last week
- Reference implementation for DPO (Direct Preference Optimization)☆2,583Updated 9 months ago
- ⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)☆962Updated 5 months ago
- Transformer related optimization, including BERT, GPT☆6,173Updated last year
- The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.☆1,106Updated this week
- Efficient Training (including pre-training and fine-tuning) for Big Models☆592Updated this week
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,534Updated last year
- real Transformer TeraFLOPS on various GPUs☆899Updated last year
- Ring attention implementation with flash attention☆771Updated last week
- Transformer based on a variant of attention that is linear complexity in respect to sequence length☆768Updated last year
- Long Range Arena for Benchmarking Efficient Transformers☆757Updated last year
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,119Updated last year
- SwissArmyTransformer is a flexible and powerful library to develop your own Transformer variants.☆1,079Updated 5 months ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,029Updated 3 weeks ago
- LightSeq: A High Performance Library for Sequence Processing and Generation☆3,277Updated 2 years ago
- Foundation Architecture for (M)LLMs☆3,076Updated last year
- The calflops is designed to calculate FLOPs、MACs and Parameters in all various neural networks, such as Linear、 CNN、 RNN、 GCN、Transformer…☆797Updated 11 months ago