From e5a8be248bf99cfb7c0e1d37cf67218e8a7346ef Mon Sep 17 00:00:00 2001 From: Julien Lin Date: Wed, 17 Sep 2025 05:55:18 +0000 Subject: [PATCH] set two H2D to non-blocking Signed-off-by: Julien Lin --- vllm/v1/attention/backends/flashinfer.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/vllm/v1/attention/backends/flashinfer.py b/vllm/v1/attention/backends/flashinfer.py index 98a4cf38bc19..bbd5b6c39150 100755 --- a/vllm/v1/attention/backends/flashinfer.py +++ b/vllm/v1/attention/backends/flashinfer.py @@ -578,9 +578,10 @@ def build(self, kv_data_type=self.kv_cache_dtype, ) else: - attn_metadata.qo_indptr_gpu = qo_indptr_cpu.to(self.device) + attn_metadata.qo_indptr_gpu = qo_indptr_cpu.to( + self.device, non_blocking=True) attn_metadata.paged_kv_indptr_gpu = paged_kv_indptr_cpu.to( - self.device) + self.device, non_blocking=True) if num_decodes > 0: pure_decode = num_prefills == 0