From 47882d72abb60fb8a612a4b44c67f5253419728b Mon Sep 17 00:00:00 2001 From: "Lin, Fanli" Date: Sun, 10 Nov 2024 17:19:45 -0800 Subject: [PATCH] update int_mm minimal pytorch version --- optimum/quanto/library/qbytes_mm.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/optimum/quanto/library/qbytes_mm.py b/optimum/quanto/library/qbytes_mm.py index 62da6f2e..22319345 100644 --- a/optimum/quanto/library/qbytes_mm.py +++ b/optimum/quanto/library/qbytes_mm.py @@ -92,7 +92,7 @@ def qbytes_mm_impl_cuda(activations: torch.Tensor, weights: torch.Tensor, output def qbytes_mm_impl_cpu(activations: torch.Tensor, weights: torch.Tensor, output_scales: torch.Tensor) -> torch.Tensor: if ( # FIXME: accuracy issues with 2.4.x - version.parse(torch.__version__).release > version.parse("2.5.0").release + version.parse(torch.__version__).release >= version.parse("2.6.0").release and activations.dtype == torch.int8 and weights.dtype == torch.int8 ):