SIGN IN SIGN UP

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

0 0 122 Python

[P/D] Dynamic `kv_output_aggregator` collect size (#26734)

Signed-off-by: NickLucche <nlucches@redhat.com>
N
Nicolò Lucchesi committed
4dfdb821c8e46781ba6a37d828a7c76bcd401ae7
Parent: 58fab50
Committed by GitHub <noreply@github.com> on 10/22/2025, 4:07:58 PM