3 results found Sort:

Zhen-Dong
HAWQ Zhen-Dong
82
413
mit
14
Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.
tvm 4-bit 8-bit hessian pytorch tensorcore distillation quantization hardware-aware mixed-precision model-compression efficient-neural-networks quantized-neural-networks
Created 2020-11-24
48 commits to main branch, last one about a year ago
wmmae
wmma_extension wmmae
14
84
mit
8
An extension library of WMMA API (Tensor Core API)
gpu matrix wmma-api tensorcore tensorcores gpu-computing gpu-programming
Created 2019-11-10
946 commits to main branch, last one 4 months ago
enp1s0
ozIMMU enp1s0
2
46
mit
4
FP64 equivalent GEMM via Int8 Tensor Cores using the Ozaki scheme
cuda gemm tensorcore tensorcores mixed-precision
Created 2023-06-14
242 commits to main branch, last one 2 months ago