bytedance / ByteTransformer
optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
☆457Updated 8 months ago
Related projects ⓘ
Alternatives and complementary repositories for ByteTransformer
- ☆140Updated 6 months ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆545Updated last month
- Running BERT without Padding☆460Updated 2 years ago
- FlagGems is an operator library for large language models implemented in Triton Language.☆342Updated this week
- ☆123Updated 2 weeks ago
- ☆289Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆359Updated 3 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆219Updated 5 months ago
- FlashInfer: Kernel Library for LLM Serving☆1,452Updated this week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆357Updated this week
- Transformer related optimization, including BERT, GPT☆60Updated last year
- A fast communication-overlapping library for tensor parallelism on GPUs.☆224Updated 3 weeks ago
- GLake: optimizing GPU memory management and IO transmission.☆379Updated 3 months ago
- A model compilation solution for various hardware☆378Updated last week
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆443Updated last week
- Microsoft Automatic Mixed Precision Library☆525Updated last month
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆311Updated 2 months ago
- ☆138Updated 2 weeks ago
- Best practice for training LLaMA models in Megatron-LM☆628Updated 10 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆238Updated last week
- A PyTorch Native LLM Training Framework☆665Updated 2 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆169Updated this week
- ☆289Updated 7 months ago
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆203Updated last week
- BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.☆816Updated this week
- A Easy-to-understand TensorOp Matmul Tutorial☆290Updated 2 months ago
- Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.☆263Updated last year
- [EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a V…☆322Updated this week
- Zero Bubble Pipeline Parallelism☆281Updated last week
- flash attention tutorial written in python, triton, cuda, cutlass☆202Updated 5 months ago