microsoft / TutelLinks
Tutel MoE: Optimized Mixture-of-Experts Library, Support GptOss/DeepSeek/Kimi-K2/Qwen3 using FP8/NVFP4/MXFP4
☆962Updated last month
Alternatives and similar repositories for Tutel
Users that are interested in Tutel are comparing it to the libraries listed below
Sorting:
- Microsoft Automatic Mixed Precision Library☆635Updated 2 months ago
- Large Context Attention☆764Updated 3 months ago
- A fast MoE impl for PyTorch☆1,829Updated 11 months ago
- Ring attention implementation with flash attention☆973Updated 4 months ago
- Pipeline Parallelism for PyTorch☆785Updated last year
- A curated reading list of research in Mixture-of-Experts(MoE).☆659Updated last year
- ☆702Updated last month
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,315Updated 10 months ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,600Updated last year
- Zero Bubble Pipeline Parallelism☆449Updated 8 months ago
- A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models☆846Updated 2 years ago
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆549Updated 8 months ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,431Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆2,224Updated 5 months ago
- Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs☆923Updated 2 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆637Updated 3 weeks ago
- Helpful tools and examples for working with flex-attention☆1,116Updated 2 weeks ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆503Updated last year
- Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"☆323Updated 11 months ago
- Best practice for training LLaMA models in Megatron-LM☆664Updated 2 years ago
- Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".☆865Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,005Updated last year
- A simple and effective LLM pruning approach.☆846Updated last year
- ☆353Updated last year
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆964Updated 10 months ago
- Latency and Memory Analysis of Transformer Models for Training and Inference☆479Updated 9 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆807Updated 10 months ago
- Fast inference from large lauguage models via speculative decoding☆884Updated last year
- Automatically split your PyTorch models on multiple GPUs for training & inference☆656Updated 2 years ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,132Updated this week