From 2b7417bf6a9e2aa59a9736716f823fd03f26f67d Mon Sep 17 00:00:00 2001 From: dmitrygx Date: Sat, 20 Sep 2025 10:30:10 +0300 Subject: [PATCH] fix(disagg): fix sending KV cache in case of MLA for NIXL backend (#10673) --- python/sglang/srt/disaggregation/nixl/conn.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python/sglang/srt/disaggregation/nixl/conn.py b/python/sglang/srt/disaggregation/nixl/conn.py index 1579209a3..b76a1cb15 100644 --- a/python/sglang/srt/disaggregation/nixl/conn.py +++ b/python/sglang/srt/disaggregation/nixl/conn.py @@ -547,7 +547,7 @@ class NixlKVManager(CommonKVManager): notif = "_".join([str(req.room), "kv", str(chunk_id), str(int(is_last))]) decode_tp_size = self.decode_kv_args_table[req.agent_name].decode_tp_size - if decode_tp_size == self.attn_tp_size: + if self.is_mla_backend or (decode_tp_size == self.attn_tp_size): kv_xfer_handle = self.send_kvcache( req.agent_name, kv_indices,