Skip to content

GitLab

Unverified Commit 53056731 authored by Yang.Tao's avatar Yang.Tao Committed by GitHub
Browse files

fix some typos : supported_head_sizes (#14627)

parent 4cbf2867
Show whitespace changes
Inline Side-by-side
Showing with 3 additions and 3 deletions
vllm/attention/backends/blocksparse_attn.py
View file @ 53056731
...@@ -335,11 +335,11 @@ class BlocksparseFlashAttentionImpl(AttentionImpl): ...@@ -335,11 +335,11 @@ class BlocksparseFlashAttentionImpl(AttentionImpl):
self.sparse_block_size = self.blocksparse_params.block_size self.sparse_block_size = self.blocksparse_params.block_size
self.head_sliding_step = self.blocksparse_params.head_sliding_step self.head_sliding_step = self.blocksparse_params.head_sliding_step
suppored_head_sizes = PagedAttention.get_supported_head_sizes() supported_head_sizes = PagedAttention.get_supported_head_sizes()
if head_size not in suppored_head_sizes: if head_size not in supported_head_sizes:
raise ValueError( raise ValueError(
f"Head size {head_size} is not supported by PagedAttention. " f"Head size {head_size} is not supported by PagedAttention. "
f"Supported head sizes are: {suppored_head_sizes}.") f"Supported head sizes are: {supported_head_sizes}.")
self.tp_size = get_tensor_model_parallel_world_size() self.tp_size = get_tensor_model_parallel_world_size()
self.tp_rank = get_tensor_model_parallel_rank() self.tp_rank = get_tensor_model_parallel_rank()
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment