ModelTC / NARTLinks
NART = NART is not A RunTime, a deep learning inference framework.
☆37Updated 2 years ago
Alternatives and similar repositories for NART
Users that are interested in NART are comparing it to the libraries listed below
Sorting:
- ☆139Updated last year
- ☆149Updated 6 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆94Updated 3 weeks ago
- ☆59Updated 8 months ago
- ☆102Updated 4 months ago
- Offline Quantization Tools for Deploy.☆131Updated last year
- OneFlow->ONNX☆43Updated 2 years ago
- ☆97Updated 3 years ago
- ☆37Updated 9 months ago
- ☆11Updated 6 months ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆74Updated 11 months ago
- ☆36Updated 3 years ago
- An unofficial cuda assembler, for all generations of SASS, hopefully :)☆83Updated 2 years ago
- play gemm with tvm☆91Updated 2 years ago
- code reading for tvm☆76Updated 3 years ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆39Updated 5 months ago
- Compiler Infrastructure for Neural Networks☆146Updated 2 years ago
- CUDA Templates for Linear Algebra Subroutines☆100Updated last year
- [MLSys 2021] IOS: Inter-Operator Scheduler for CNN Acceleration☆200Updated 3 years ago
- A set of examples around MegEngine☆31Updated last year
- ☆44Updated 4 years ago
- ☆137Updated last year
- symmetric int8 gemm☆66Updated 5 years ago
- ☆236Updated 2 years ago
- ☆154Updated 2 years ago
- This repository contains integer operators on GPUs for PyTorch.☆208Updated last year
- Inference of quantization aware trained networks using TensorRT☆83Updated 2 years ago
- ☆128Updated 7 months ago
- ☆96Updated 10 months ago
- Benchmark scripts for TVM☆75Updated 3 years ago