bytedance / ByteTransformer
optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
☆457Updated 7 months ago
Related projects ⓘ
Alternatives and complementary repositories for ByteTransformer
- FlagGems is an operator library for large language models implemented in Triton Language.☆328Updated this week
- ☆123Updated this week
- ☆140Updated 6 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆215Updated 5 months ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆541Updated 3 weeks ago
- Running BERT without Padding☆460Updated 2 years ago
- Disaggregated serving system for Large Language Models (LLMs).☆348Updated 2 months ago
- ☆282Updated last week
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆433Updated 2 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆352Updated last week
- A fast communication-overlapping library for tensor parallelism on GPUs.☆217Updated last week
- ☆136Updated this week
- [EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a V…☆315Updated this week
- Microsoft Automatic Mixed Precision Library☆522Updated last month
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆310Updated last month
- GLake: optimizing GPU memory management and IO transmission.☆375Updated 3 months ago
- FlashInfer: Kernel Library for LLM Serving☆1,395Updated this week
- ☆283Updated 7 months ago
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆200Updated 3 weeks ago
- A Easy-to-understand TensorOp Matmul Tutorial☆287Updated last month
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆611Updated 2 months ago
- Transformer related optimization, including BERT, GPT☆60Updated last year
- FlagScale is a large model toolkit based on open-sourced projects.☆167Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆222Updated this week
- Zero Bubble Pipeline Parallelism☆279Updated this week
- LLaMa/RWKV onnx models, quantization and testcase☆350Updated last year
- Best practice for training LLaMA models in Megatron-LM☆627Updated 10 months ago
- Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.☆264Updated last year
- flash attention tutorial written in python, triton, cuda, cutlass☆194Updated 4 months ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆26Updated 2 months ago