bytedance / ByteTransformer
optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
☆473Updated last year
Alternatives and similar repositories for ByteTransformer
Users that are interested in ByteTransformer are comparing it to the libraries listed below
Sorting:
- ☆127Updated 4 months ago
- ☆139Updated last year
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆718Updated 3 months ago
- Running BERT without Padding☆471Updated 3 years ago
- FlagGems is an operator library for large language models implemented in Triton Language.☆516Updated this week
- ☆329Updated 3 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆266Updated 11 months ago
- GLake: optimizing GPU memory management and IO transmission.☆460Updated last month
- Dynamic Memory Management for Serving LLMs without PagedAttention☆366Updated 3 weeks ago
- Distributed Triton for Parallel Systems☆677Updated last week
- Zero Bubble Pipeline Parallelism☆387Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆580Updated last month
- ☆131Updated 2 months ago
- ☆148Updated 4 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆270Updated this week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆490Updated 3 weeks ago
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆238Updated 3 weeks ago
- A model compilation solution for various hardware☆430Updated this week
- Best practice for training LLaMA models in Megatron-LM☆650Updated last year
- Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.☆267Updated 2 years ago
- Transformer related optimization, including BERT, GPT☆59Updated last year
- Yinghan's Code Sample☆327Updated 2 years ago
- A Easy-to-understand TensorOp Matmul Tutorial☆346Updated 7 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆818Updated 8 months ago
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆245Updated this week
- Microsoft Automatic Mixed Precision Library☆595Updated 7 months ago
- A low-latency & high-throughput serving engine for LLMs☆354Updated 3 weeks ago
- BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.☆863Updated 4 months ago
- FlagPerf is an open-source software platform for benchmarking AI chips.☆331Updated this week
- Materials for learning SGLang☆406Updated 2 weeks ago