7 results found Sort:

NVIDIA
OpenSeq2Seq NVIDIA
369
1.6k
apache-2.0
92
Toolkit for efficient experimentation with Speech Recognition, Text2Speech and NLP
float16 seq2seq multi-gpu multi-node tensorflow deep-learning language-model speech-to-text text-to-speech mixed-precision speech-synthesis speech-recognition sequence-to-sequence neural-machine-translation
This repository has been archived (exclude archived)
Created 2017-09-08
1,695 commits to master branch, last one 4 years ago
ashvardanian
SimSIMD ashvardanian
68
1.2k
apache-2.0
20
Up to 200x Faster Dot Products & Similarity Metrics — for Python, Rust, C, JS, and Swift, supporting f64, f32, f16 real & complex, i8, and bit vectors using SIMD for both AVX2, AVX-512, NEON, SVE, & S...
avx2 blas neon simd numpy scipy avx512 arm-sve float16 metrics arm-neon assembly bfloat16 vector-search blas-libraries simd-instructions similarity-search similarity-measures distance-calculation information-retrieval
Created 2023-03-14
1,189 commits to main branch, last one 6 days ago
starkat99
half-rs starkat99
56
236
other
12
Half-precision floating point types f16 and bf16 for Rust.
f16 rust crates float16 ieee754 bfloat16 binary16 rust-embedded floating-point
Created 2016-02-24
352 commits to main branch, last one 9 months ago
petamoriken
float16 petamoriken
7
98
mit
7
Stage 3 IEEE 754 half-precision floating-point ponyfill
fp16 float16 ieee754 binary16 javascript typescript float16array half-precision
Created 2017-05-05
1,907 commits to master branch, last one a day ago
x448
float16 x448
8
68
mit
4
float16 provides IEEE 754 half-precision format (binary16) with correct conversions to/from float32
go golang float16 ieee754 binary16 floating-point half-precision
Created 2019-12-28
137 commits to master branch, last one 11 days ago
andreped
GradientAccumulator andreped
11
53
mit
3
:dart: Accumulated Gradients for TensorFlow 2
gpu tf2 tpu keras float16 multi-gpu batch-size tensorflow huggingface tensorflow2 deep-learning hacktoberfest mixed-precision memory-constraints distributed-training accumulated-gradients gradient-accumulation adaptive-gradient-clipping accumulated-batch-normalization
Created 2022-05-31
698 commits to main branch, last one about a year ago
aredden
torch-cublas-hgemm aredden
3
48
unknown
2
PyTorch half precision gemm lib w/ fused optional bias + optional relu/gelu
cuda gemm float16 pytorch
Created 2024-04-10
14 commits to master branch, last one about a month ago