17 results found Sort:

207
2.6k
apache-2.0
34
Build, customize and control you own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJ...
Created 2023-03-19
593 commits to main branch, last one 5 months ago
369
1.6k
apache-2.0
91
Toolkit for efficient experimentation with Speech Recognition, Text2Speech and NLP
This repository has been archived (exclude archived)
Created 2017-09-08
1,695 commits to master branch, last one 4 years ago
48
581
mit
11
Microsoft Automatic Mixed Precision Library
Created 2023-01-30
98 commits to main branch, last one 6 months ago
81
429
mit
14
Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.
Created 2020-11-24
48 commits to main branch, last one about a year ago
85
380
mit
19
[CVPR 2019, Oral] HAQ: Hardware-Aware Automated Quantization with Mixed Precision
Created 2019-06-14
15 commits to master branch, last one 4 years ago
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation
Created 2019-01-26
106 commits to master branch, last one 3 years ago
18
110
mit
3
High Resolution Style Transfer in PyTorch with Color Control and Mixed Precision :art:
Created 2020-09-18
55 commits to master branch, last one 2 years ago
A tool for debugging and assessing floating point precision and reproducibility.
Created 2015-04-20
791 commits to master branch, last one about a month ago
8
65
unknown
1
[ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
Created 2024-06-02
56 commits to viditq branch, last one 25 days ago
8
64
apache-2.0
4
NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference
Created 2022-12-19
674 commits to master branch, last one 3 months ago
11
58
unknown
3
基于tensorflow1.x的预训练模型调用,支持单机多卡、梯度累积,XLA加速,混合精度。可灵活训练、验证、预测。
Created 2020-09-21
94 commits to master branch, last one 3 years ago
FP64 equivalent GEMM via Int8 Tensor Cores using the Ozaki scheme
Created 2023-06-14
245 commits to main branch, last one about a month ago
BitPack is a practical tool to efficiently save ultra-low precision/mixed-precision quantized models.
Created 2021-02-08
19 commits to main branch, last one 2 years ago
7
39
apache-2.0
7
PDPU: An Open-Source Posit Dot-Product Unit for Deep Learning Applications
Created 2022-11-13
41 commits to main branch, last one about a year ago
4
33
unknown
2
[ECCV24] MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
Created 2024-06-02
14 commits to master branch, last one 3 months ago