bytedance / ByteTransformer
optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
☆469Updated 10 months ago
Alternatives and similar repositories for ByteTransformer:
Users that are interested in ByteTransformer are comparing it to the libraries listed below
- ☆127Updated last month
- FlagGems is an operator library for large language models implemented in Triton Language.☆406Updated this week
- A collection of memory efficient attention operators implemented in the Triton language.☆233Updated 7 months ago
- ☆311Updated last week
- ☆140Updated 9 months ago
- Running BERT without Padding☆468Updated 2 years ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆607Updated last week
- A fast communication-overlapping library for tensor parallelism on GPUs.☆280Updated 3 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆453Updated 5 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆415Updated 3 weeks ago
- FlagScale is a large model toolkit based on open-sourced projects.☆209Updated this week
- Zero Bubble Pipeline Parallelism☆317Updated 2 months ago
- GLake: optimizing GPU memory management and IO transmission.☆424Updated 2 months ago
- ☆211Updated last year
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆219Updated 2 weeks ago
- ☆142Updated 2 weeks ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆377Updated 4 months ago
- Transformer related optimization, including BERT, GPT☆59Updated last year
- Microsoft Automatic Mixed Precision Library☆553Updated 4 months ago
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆492Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆273Updated last month
- Best practice for training LLaMA models in Megatron-LM☆641Updated last year
- ☆311Updated 9 months ago
- A model compilation solution for various hardware☆398Updated 3 weeks ago
- ☆598Updated 7 months ago
- A PyTorch Native LLM Training Framework☆698Updated last month
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆689Updated 4 months ago
- Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.☆266Updated last year
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆34Updated 4 months ago
- A baseline repository of Auto-Parallelism in Training Neural Networks☆142Updated 2 years ago