fix(llama.cpp): Enable parallel requests (#1616)
integrate changes from llama.cpp Signed-off-by: Sebastian <tauven@gmail.com>
S
Sebastian committed
eaf85a30f95d9cd0ded04a7957b4be0b8d8e7a2f
Parent: 6a88b03
Committed by GitHub <noreply@github.com>
on 1/21/2024, 8:56:14 AM