From 27efe54956775b46eee9e2fdbd91449f5b548dbb Mon Sep 17 00:00:00 2001 From: Jee Jee Li Date: Tue, 29 Jul 2025 09:25:39 +0000 Subject: [PATCH] Done Signed-off-by: Jee Jee Li --- .../layers/fused_moe/deepep_ll_prepare_finalize.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py b/vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py index 57871ca250ae..cfc2bdcf0240 100644 --- a/vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py +++ b/vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py @@ -40,7 +40,7 @@ class DeepEPLLPrepareAndFinalize(mk.FusedMoEPrepareAndFinalize): # DeepEP low-latency kernels are compiled only for certain # specific hidden sizes. - SUPPORTED_HIDDEN_SIZES = [2048, 2560, 4096, 5120, 7168] + SUPPORTED_HIDDEN_SIZES = [2048, 2560, 4096, 5120, 6144, 7168] def __init__(self, buffer: deep_ep.Buffer,