[5/N][Attention] Finish eliminating `vllm/attention` folder (#32064)

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

[5/N][Attention] Finish eliminating `vllm/attention` folder (#32064)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
a608b4c6 · Matthew Bonanni · GitHub · 1f3a2c29 · a608b4c6 · a608b4c6
Unverified Commit a608b4c6 authored Jan 27, 2026 by Matthew Bonanni Committed by GitHub Jan 27, 2026
11 changed files
--- a/vllm/model_executor/models/step3_text.py
+++ b/vllm/model_executor/models/step3_text.py
--- a/vllm/model_executor/models/step3_vl.py
+++ b/vllm/model_executor/models/step3_vl.py
--- a/vllm/model_executor/models/transformers/base.py
+++ b/vllm/model_executor/models/transformers/base.py
--- a/vllm/model_executor/models/whisper.py
+++ b/vllm/model_executor/models/whisper.py
--- a/vllm/model_executor/models/whisper_causal.py
+++ b/vllm/model_executor/models/whisper_causal.py
--- a/vllm/model_executor/models/zamba2.py
+++ b/vllm/model_executor/models/zamba2.py
--- a/vllm/v1/attention/backends/flash_attn.py
+++ b/vllm/v1/attention/backends/flash_attn.py
--- a/vllm/v1/attention/backends/rocm_aiter_fa.py
+++ b/vllm/v1/attention/backends/rocm_aiter_fa.py
--- a/vllm/v1/spec_decode/draft_model.py
+++ b/vllm/v1/spec_decode/draft_model.py
--- a/vllm/v1/worker/gpu_model_runner.py
+++ b/vllm/v1/worker/gpu_model_runner.py
--- a/vllm/v1/worker/utils.py
+++ b/vllm/v1/worker/utils.py