From fefa19fec05295a6098cbc6d630b97cc697ff914 Mon Sep 17 00:00:00 2001 From: miter Date: Sat, 24 May 2025 06:20:21 +0800 Subject: [PATCH] Update cmdline --enable-dp-attention help string for Qwen 2/3 Moe models. (#6524) Signed-off-by: miter --- python/sglang/srt/server_args.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python/sglang/srt/server_args.py b/python/sglang/srt/server_args.py index 40b41b036..e7a102c91 100644 --- a/python/sglang/srt/server_args.py +++ b/python/sglang/srt/server_args.py @@ -1138,7 +1138,7 @@ class ServerArgs: parser.add_argument( "--enable-dp-attention", action="store_true", - help="Enabling data parallelism for attention and tensor parallelism for FFN. The dp size should be equal to the tp size. Currently only DeepSeek-V2 is supported.", + help="Enabling data parallelism for attention and tensor parallelism for FFN. The dp size should be equal to the tp size. Currently DeepSeek-V2 and Qwen 2/3 MoE models are supported.", ) parser.add_argument( "--enable-dp-lm-head",