bytedance / ByteTransformer
optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
☆471Updated last year
Alternatives and similar repositories for ByteTransformer:
Users that are interested in ByteTransformer are comparing it to the libraries listed below
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆678Updated 2 months ago
- ☆324Updated 2 months ago
- ☆139Updated 11 months ago
- ☆127Updated 3 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆257Updated 9 months ago
- Running BERT without Padding☆471Updated 3 years ago
- Transformer related optimization, including BERT, GPT☆59Updated last year
- FlagGems is an operator library for large language models implemented in Triton Language.☆467Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆517Updated 7 months ago
- ☆145Updated 2 months ago
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆233Updated last week
- Zero Bubble Pipeline Parallelism☆375Updated 3 weeks ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆458Updated last week
- GLake: optimizing GPU memory management and IO transmission.☆451Updated last week
- A model compilation solution for various hardware☆416Updated 2 weeks ago
- BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.☆853Updated 3 months ago
- Microsoft Automatic Mixed Precision Library☆587Updated 6 months ago
- Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.☆267Updated 2 years ago
- ☆128Updated 3 weeks ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆333Updated last week
- Materials for learning SGLang☆355Updated last week
- FlagScale is a large model toolkit based on open-sourced projects.☆257Updated this week
- Best practice for training LLaMA models in Megatron-LM☆645Updated last year
- ☆214Updated last year
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆242Updated 5 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆783Updated 6 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆111Updated 3 months ago
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆240Updated 3 weeks ago
- A Easy-to-understand TensorOp Matmul Tutorial☆332Updated 6 months ago
- The road to hack SysML and become an system expert☆476Updated 6 months ago