From 4ac462bfb84ab284b573c13b2b2e782ba41464c9 Mon Sep 17 00:00:00 2001 From: Victor SANH Date: Thu, 28 May 2020 10:41:53 -0400 Subject: [PATCH] Update examples/movement-pruning/README.md Co-authored-by: Julien Chaumond --- examples/movement-pruning/README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/examples/movement-pruning/README.md b/examples/movement-pruning/README.md index cc76d03f55..57383aa5c4 100644 --- a/examples/movement-pruning/README.md +++ b/examples/movement-pruning/README.md @@ -163,6 +163,7 @@ For reproducibility purposes, we share the detailed results presented in the pap Early experiments show that even though models fine-pruned with (soft) movement pruning are extremely sparse, they do not benefit from significant improvement in terms of inference speed when using the standard PyTorch inference. We are currently benchmarking and exploring inference setups specifically for sparse architectures. +In particular, hardware manufacturers are announcing devices that will speedup inference for sparse networks considerably. ## Citation