From 323a05b3c5264c9734180189f966489647722db3 Mon Sep 17 00:00:00 2001 From: Woosuk Kwon Date: Thu, 18 Sep 2025 15:51:36 -0700 Subject: [PATCH] update Signed-off-by: Woosuk Kwon --- vllm/v1/worker/gpu/attn_utils.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/vllm/v1/worker/gpu/attn_utils.py b/vllm/v1/worker/gpu/attn_utils.py index 631bcd8023526..f23b9187361fa 100644 --- a/vllm/v1/worker/gpu/attn_utils.py +++ b/vllm/v1/worker/gpu/attn_utils.py @@ -136,4 +136,4 @@ def init_kv_cache( kv_cache_raw_tensors = _allocate_kv_cache(kv_cache_config, device) kv_caches = _reshape_kv_cache(kv_cache_config, kv_cache_raw_tensors, attn_backends) - bind_kv_cache(forward_context, kv_caches, runner_kv_caches) + bind_kv_cache(kv_caches, forward_context, runner_kv_caches)