forked from Karylab-cklius/vllm
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com> # Conflicts: # docs/design/attention_backends.md # vllm/distributed/kv_transfer/kv_connector/v1/nixl/base_worker.py # vllm/v1/worker/gpu/cudagraph_utils.py # vllm/v1/worker/gpu/spec_decode/autoregressive/cudagraph_utils.py