bytedance / ByteTransformerLinks
optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
☆474Updated last year
Alternatives and similar repositories for ByteTransformer
Users that are interested in ByteTransformer are comparing it to the libraries listed below
Sorting:
- ☆127Updated 5 months ago
- ☆139Updated last year
- Running BERT without Padding☆471Updated 3 years ago
- ☆336Updated this week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆801Updated 2 weeks ago
- A collection of memory efficient attention operators implemented in the Triton language.☆272Updated last year
- Transformer related optimization, including BERT, GPT☆59Updated last year
- ☆148Updated 5 months ago
- FlagGems is an operator library for large language models implemented in the Triton Language.☆573Updated this week
- Zero Bubble Pipeline Parallelism☆398Updated last month
- A model compilation solution for various hardware☆437Updated this week
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆246Updated last week
- ☆141Updated 3 months ago
- GLake: optimizing GPU memory management and IO transmission.☆467Updated 2 months ago
- Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.☆267Updated 2 years ago
- ☆219Updated last year
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆252Updated 7 months ago
- LiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training☆406Updated last week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆519Updated 3 weeks ago
- BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.☆873Updated 5 months ago
- Distributed Compiler Based on Triton for Parallel Systems☆829Updated this week
- FlagScale is a large model toolkit based on open-sourced projects.☆307Updated this week
- Materials for learning SGLang☆443Updated this week
- PyTorch distributed training acceleration framework☆49Updated 4 months ago
- Microsoft Automatic Mixed Precision Library☆609Updated 8 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆396Updated 3 weeks ago
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆55Updated 10 months ago
- MegCC是一个运行时超轻量，高效，移植简单的深度学习模型编译器☆485Updated 7 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆617Updated 2 months ago
- ☆135Updated last year