SIGN IN SIGN UP

A high-throughput and memory-efficient inference and serving engine for LLMs

0 0 122 Python

[Misc] Refactor `get_kv_cache_spec` into `AttentionLayerBase` (#26587)

Signed-off-by: NickLucche <nlucches@redhat.com>
N
Nicolò Lucchesi committed
b26b70bec4faa3dae487db1f3eebaddd86c1d828
Parent: ab4be40
Committed by GitHub <noreply@github.com> on 10/18/2025, 1:51:21 PM