void-main / FasterTransformerLinks
Transformer related optimization, including BERT, GPT
☆59Updated 2 years ago
Alternatives and similar repositories for FasterTransformer
Users that are interested in FasterTransformer are comparing it to the libraries listed below
Sorting:
- ☆141Updated last year
- ☆129Updated 9 months ago
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆478Updated last year
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆40Updated 7 months ago
- Transformer related optimization, including BERT, GPT☆39Updated 2 years ago
- Running BERT without Padding☆475Updated 3 years ago
- A collection of memory efficient attention operators implemented in the Triton language.☆279Updated last year
- An easy-to-use package for implementing SmoothQuant for LLMs☆106Updated 5 months ago
- ☆79Updated last year
- export llama to onnx☆135Updated 9 months ago
- ☆150Updated 8 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆151Updated last month
- ☆147Updated 6 months ago
- ☆199Updated 4 months ago
- ☆98Updated last year
- ☆59Updated 10 months ago
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆65Updated last year
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆140Updated last month
- ☆21Updated 2 years ago
- Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"☆315Updated 6 months ago
- Zero Bubble Pipeline Parallelism☆427Updated 4 months ago
- Simple Dynamic Batching Inference☆146Updated 3 years ago
- ☆220Updated 2 years ago
- ☆121Updated last year
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆94Updated 2 weeks ago
- ☆139Updated last year
- A quantization algorithm for LLM☆143Updated last year
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆265Updated last month
- LLaMa/RWKV onnx models, quantization and testcase☆365Updated 2 years ago
- ☆95Updated 6 months ago