vllm/v1/attention/backends/utils.py · 070da660c1bf9e7a7be8b9efeff4b06f91c7342f · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[Kernel] Simplify `get_kv_cache_layout` and cache `use_trtllm_attention` env-dependent bit (#22735) · 070da660
Nicolò Lucchesi authored Aug 16, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
070da660

utils.py 26.9 KB