[Chore] Clean up pytorch helper functions in `vllm.utils` (#26908)

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn> Signed-off-by: isotr0py <2037008807@qq.com>

[Chore] Clean up pytorch helper functions in `vllm.utils` (#26908)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn> Signed-off-by: isotr0py <2037008807@qq.com>
6ac5e06f · Isotr0py · GitHub · 5c2acb27 · 6ac5e06f · 6ac5e06f
Unverified Commit 6ac5e06f authored Oct 19, 2025 by Isotr0py Committed by GitHub Oct 18, 2025
19 changed files
--- a/vllm/model_executor/models/plamo2.py
+++ b/vllm/model_executor/models/plamo2.py
--- a/vllm/model_executor/models/qwen3_next.py
+++ b/vllm/model_executor/models/qwen3_next.py
--- a/vllm/model_executor/models/transformers/moe.py
+++ b/vllm/model_executor/models/transformers/moe.py
--- a/vllm/model_executor/models/utils.py
+++ b/vllm/model_executor/models/utils.py
--- a/vllm/model_executor/models/whisper.py
+++ b/vllm/model_executor/models/whisper.py
--- a/vllm/model_executor/utils.py
+++ b/vllm/model_executor/utils.py
--- a/vllm/platforms/__init__.py
+++ b/vllm/platforms/__init__.py
--- a/vllm/platforms/cuda.py
+++ b/vllm/platforms/cuda.py
--- a/vllm/platforms/rocm.py
+++ b/vllm/platforms/rocm.py
--- a/vllm/usage/usage_lib.py
+++ b/vllm/usage/usage_lib.py
--- a/vllm/utils/__init__.py
+++ b/vllm/utils/__init__.py
--- a/vllm/utils/torch_utils.py
+++ b/vllm/utils/torch_utils.py
--- a/vllm/v1/attention/backends/flex_attention.py
+++ b/vllm/v1/attention/backends/flex_attention.py
--- a/vllm/v1/attention/backends/rocm_aiter_fa.py
+++ b/vllm/v1/attention/backends/rocm_aiter_fa.py
--- a/vllm/v1/kv_cache_interface.py
+++ b/vllm/v1/kv_cache_interface.py
--- a/vllm/v1/sample/ops/penalties.py
+++ b/vllm/v1/sample/ops/penalties.py
--- a/vllm/v1/worker/gpu_model_runner.py
+++ b/vllm/v1/worker/gpu_model_runner.py
--- a/vllm/v1/worker/tpu_worker.py
+++ b/vllm/v1/worker/tpu_worker.py
--- a/vllm/v1/worker/ubatching.py
+++ b/vllm/v1/worker/ubatching.py