From fc3ac8075b081defebe49ef3610c6210d9b5107b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Dani=C3=ABl=20de=20Kok?= <me@danieldk.eu>
Date: Fri, 7 Feb 2025 20:13:50 +0000
Subject: [PATCH] Remove outdated TODO

---
 server/text_generation_server/layers/fp8.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/server/text_generation_server/layers/fp8.py b/server/text_generation_server/layers/fp8.py
index fe138a4af72..04689ed9233 100644
--- a/server/text_generation_server/layers/fp8.py
+++ b/server/text_generation_server/layers/fp8.py
@@ -23,7 +23,6 @@
     quantization = None
 
 try:
-    # TODO: needs to be ported over to MoE and used on CUDA.
     from moe_kernels.fp8_utils import w8a8_block_fp8_matmul, per_token_group_quant_fp8
 except ImportError:
     w8a8_block_fp8_matmul = None