[Feature] Add AllGather-KV sequence-parallel attention str… (#4968)

Signed-off-by: zhuhh97 <zhuhonghan@huawei.com>
Signed-off-by: dph97 <nenbaying@163.com>
Signed-off-by: zhuhh97 <zhh@unknown>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: dengyunyang <584797741@qq.com>

vllm_omni/diffusion/worker/diffusion_worker.py

@@ -315,6 +315,7 @@ class DiffusionWorker:
                 sequence_parallel_size=parallel_config.sequence_parallel_size,
                 ulysses_degree=parallel_config.ulysses_degree,
                 ring_degree=parallel_config.ring_degree,
+                allgather_degree=parallel_config.allgather_degree,
                 tensor_parallel_size=parallel_config.tensor_parallel_size,
                 pipeline_parallel_size=parallel_config.pipeline_parallel_size,
                 fully_shard_degree=parallel_config.hsdp_shard_size if parallel_config.use_hsdp else 1,