[1/N][Attention] Restructure attention: move files (#31916)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>

[1/N][Attention] Restructure attention: move files (#31916)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
2612ba92 · Matthew Bonanni · GitHub · 1f8b7c53 · 2612ba92 · 2612ba92
Unverified Commit 2612ba92 authored Jan 09, 2026 by Matthew Bonanni Committed by GitHub Jan 09, 2026
20 changed files
--- a/vllm/v1/attention/backends/mla/rocm_aiter_mla.py
+++ b/vllm/v1/attention/backends/mla/rocm_aiter_mla.py
--- a/vllm/v1/attention/backends/mla/rocm_aiter_mla_sparse.py
+++ b/vllm/v1/attention/backends/mla/rocm_aiter_mla_sparse.py
--- a/vllm/v1/attention/backends/mla/triton_mla.py
+++ b/vllm/v1/attention/backends/mla/triton_mla.py
--- a/vllm/attention/backends/registry.py
+++ b/vllm/attention/backends/registry.py
--- a/vllm/v1/attention/backends/rocm_aiter_fa.py
+++ b/vllm/v1/attention/backends/rocm_aiter_fa.py
--- a/vllm/v1/attention/backends/rocm_aiter_unified_attn.py
+++ b/vllm/v1/attention/backends/rocm_aiter_unified_attn.py
--- a/vllm/v1/attention/backends/rocm_attn.py
+++ b/vllm/v1/attention/backends/rocm_attn.py
--- a/vllm/v1/attention/backends/short_conv_attn.py
+++ b/vllm/v1/attention/backends/short_conv_attn.py
--- a/vllm/v1/attention/backends/tree_attn.py
+++ b/vllm/v1/attention/backends/tree_attn.py
--- a/vllm/v1/attention/backends/triton_attn.py
+++ b/vllm/v1/attention/backends/triton_attn.py
--- a/vllm/v1/attention/backends/utils.py
+++ b/vllm/v1/attention/backends/utils.py
--- a/vllm/attention/layers/__init__.py
+++ b/vllm/attention/layers/__init__.py
--- a/vllm/attention/ops/chunked_prefill_paged_decode.py
+++ b/vllm/attention/ops/chunked_prefill_paged_decode.py
--- a/vllm/attention/ops/common.py
+++ b/vllm/attention/ops/common.py
--- a/vllm/attention/ops/flashmla.py
+++ b/vllm/attention/ops/flashmla.py
--- a/vllm/attention/ops/merge_attn_states.py
+++ b/vllm/attention/ops/merge_attn_states.py
--- a/vllm/attention/ops/paged_attn.py
+++ b/vllm/attention/ops/paged_attn.py
--- a/vllm/attention/ops/pallas_kv_cache_update.py
+++ b/vllm/attention/ops/pallas_kv_cache_update.py
--- a/vllm/attention/ops/prefix_prefill.py
+++ b/vllm/attention/ops/prefix_prefill.py
--- a/vllm/attention/ops/rocm_aiter_mla_sparse.py
+++ b/vllm/attention/ops/rocm_aiter_mla_sparse.py