From 7a821f0e7f6594496a6b2229e994a2868d0adc7e Mon Sep 17 00:00:00 2001 From: Tyler Michael Smith Date: Fri, 20 Jun 2025 14:41:20 +0000 Subject: [PATCH] precommit Signed-off-by: Tyler Michael Smith --- vllm/model_executor/layers/fused_moe/layer.py | 1 + 1 file changed, 1 insertion(+) diff --git a/vllm/model_executor/layers/fused_moe/layer.py b/vllm/model_executor/layers/fused_moe/layer.py index 98733f101acb3..4ed10e60b13ac 100644 --- a/vllm/model_executor/layers/fused_moe/layer.py +++ b/vllm/model_executor/layers/fused_moe/layer.py @@ -380,6 +380,7 @@ class FusedMoEMethodBase(QuantizeMethodBase): # Note : We may want to use FP8 dispatch even otherwise just to # reduce datamovement + assert act_quant_block_size is not None use_fp8_dispatch = (quant_dtype == current_platform.fp8_dtype() and act_quant_block_size[1] == DEEPEP_QUANT_BLOCK_SIZE)