A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 13, 10:45 UTC
[Misc] fix typo in DCP comment (#28389)
Signed-off-by: Livinfly <luojie3m@gmail.com>
Jie Luo committed
Nov 12, 2025 at 02:59 UTC
8c32c6e4b485f1cae1a1dc8a3f9895cf63f3e7af
1 file changed
+1
-1
vllm/v1/attention/backends/mla/common.py
+1
-1
@@ -2000,7 +2000,7 @@ class MLACommonImpl(MLACommonBaseImpl[M], Generic[M]):
2000
decode_q, kv_cache, attn_metadata, layer
2001
)
2002
2003
- # recorect dcp attn_out with lse.
2003
+ # correct dcp attn_out with lse.
2004
if self.dcp_world_size > 1:
2005
attn_out = cp_lse_ag_out_rs(attn_out, lse, get_dcp_group())
2006