From 8ca76b2af10fcfa7e035ae770db1d9c7a11ae685 Mon Sep 17 00:00:00 2001 From: Noam Gat Date: Thu, 18 Jul 2024 08:51:57 +0300 Subject: [PATCH] Update flashinfer.py --- vllm/attention/backends/flashinfer.py | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/vllm/attention/backends/flashinfer.py b/vllm/attention/backends/flashinfer.py index cd4483ed27811..9c25b2cc2ba97 100644 --- a/vllm/attention/backends/flashinfer.py +++ b/vllm/attention/backends/flashinfer.py @@ -13,15 +13,14 @@ import torch from vllm import _custom_ops as ops -from vllm.attention.backends.abstract import (AttentionBackend, - AttentionImpl, +from vllm.attention.backends.abstract import (AttentionBackend, AttentionImpl, AttentionMetadata, AttentionMetadataBuilder, AttentionType) -from vllm.attention.ops.paged_attn import PagedAttention from vllm.attention.backends.utils import (PAD_SLOT_ID, compute_slot_mapping, compute_slot_mapping_start_idx, is_block_tables_empty) +from vllm.attention.ops.paged_attn import PagedAttention from vllm.sequence import SequenceGroupMetadata from vllm.utils import get_kv_cache_torch_dtype, make_tensor_with_pad