llama.cpp
memory : avoid allocating V cache for indexer (it's not used) in Qwen3.8-Flash-Next (qwen4exp)
#28330
Open
Open
memory : avoid allocating V cache for indexer (it's not used) in Qwen3.8-Flash-Next (qwen4exp) #28330
fairydreaming
wants to merge
1 commit into
ggml-org:master
from
fairydreaming:qwen4exp-no-indexer-v-cache
memory : avoid allocating V cache for indexer (it's not used)
b12a411b
pwilkin
approved these changes
on 2026-09-03
Login to write a write a comment.
Login via GitHub