PyTorch native quantization and sparsity for training and inference
Python 2.22 k
17 小时前
A library written in C for converting between float8 (8-bit minifloat numbers) and float32 (single-precision floating-point numbers) formats.
C 2
1 个月前
Go 2
1 年前
Official Code for the paper ELMO : Efficiency via Low-precision and Peak Memory Optimization in Large Output Spaces (in ICML 2025)
Python 2
16 天前
#计算机科学#A modular, accelerator‑ready ML framework that speaks float8/16/32/64, imports models via ONNX, and trains Transformer‑class networks entirely in Go.
1
3 天前