From 53f9b180861ef7f39a8886f252cc88733d8f8c6c Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Tue, 8 Oct 2024 09:28:07 +0200 Subject: [PATCH] Black --- server/text_generation_server/layers/attention/kv_cache.py | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/server/text_generation_server/layers/attention/kv_cache.py b/server/text_generation_server/layers/attention/kv_cache.py index ced4b5b4..3960c954 100644 --- a/server/text_generation_server/layers/attention/kv_cache.py +++ b/server/text_generation_server/layers/attention/kv_cache.py @@ -24,10 +24,8 @@ class KVCache: ): """Construct the key-value cache for a layer.""" - if ( - dtype == torch.float8_e5m2 - and (ATTENTION != "flashinfer" - or SYSTEM != "cuda") + if dtype == torch.float8_e5m2 and ( + ATTENTION != "flashinfer" or SYSTEM != "cuda" ): raise ValueError( "float8_e5m2 KV cache is currently only supported for flashinfer on CUDA"