vllm.v1.attention.backends
Modules:
| Name | Description |
|---|---|
flash_attn |
Attention layer with FlashAttention. |
flashinfer |
Attention layer with FlashInfer. |
mla |
|
pallas |
|
triton_attn |
Attention layer with PagedAttention and Triton prefix prefill. |
utils |
|