tigert1998 / qatLinks
Manually implemented quantization-aware training
☆21Updated 2 years ago
Alternatives and similar repositories for qat
Users that are interested in qat are comparing it to the libraries listed below
Sorting:
- ☆206Updated 3 years ago
- ☆161Updated 2 years ago
- To deploy Transformer models in CV to mobile devices.☆18Updated 3 years ago
- ☆68Updated 2 years ago
- ☆241Updated 2 years ago
- PyTorch Quantization Aware Training Example☆140Updated last year
- [ICLR 2022 Oral] F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization☆95Updated 3 years ago
- PyTorch implementation of "Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference"☆58Updated 6 years ago
- ☆158Updated 2 years ago
- CUDA project for uni subject☆26Updated 4 years ago
- [MLSys 2021] IOS: Inter-Operator Scheduler for CNN Acceleration☆200Updated 3 years ago
- This is a demo how to write a high performance convolution run on apple silicon☆54Updated 3 years ago
- Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming☆99Updated 4 years ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆94Updated 3 weeks ago
- play gemm with tvm☆91Updated 2 years ago
- CUDA Templates for Linear Algebra Subroutines☆100Updated last year
- Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming☆36Updated 2 years ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆40Updated 7 months ago
- PyTorch extension for emulating FP8 data formats on standard FP32 Xeon/GPU hardware.☆111Updated 10 months ago
- Benchmark scripts for TVM☆74Updated 3 years ago
- Benchmark code for the "Online normalizer calculation for softmax" paper☆101Updated 7 years ago
- study of Ampere' Sparse Matmul☆18Updated 4 years ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆116Updated last year
- Neural Network Quantization & Low-Bit Fixed Point Training For Hardware-Friendly Algorithm Design☆160Updated 4 years ago
- Dynamic Tensor Rematerialization prototype (modified PyTorch) and simulator. Paper: https://arxiv.org/abs/2006.09616☆132Updated 2 years ago
- FakeQuantize with Learned Step Size(LSQ+) as Observer in PyTorch☆35Updated 3 years ago
- Post-training sparsity-aware quantization☆34Updated 2 years ago
- ☆98Updated 4 years ago
- pytorch-profiler☆51Updated 2 years ago
- Inference of quantization aware trained networks using TensorRT☆83Updated 2 years ago