llama.cpp
llama : allocate GLM_DSA indexer cache only in "full" indexer layers
#26474

Merged

llama : allocate GLM_DSA indexer cache only in "full" indexer layers #26474

fairydreaming merged 2 commits into ggml-org:master from fairydreaming:glm-lid-cache-filter

llama : allocate indexer cache only in "full" indexer layers

bda1f551

Merge remote-tracking branch 'upstream/master' into glm-lid-cache-filter

32326ca9

fairydreaming marked this pull request as ready for review 16 days ago

fairydreaming requested a review from

CISC 16 days ago

fairydreaming requested a review from

ggerganov 16 days ago

CISC approved these changes on 2026-08-03

ggerganov approved these changes on 2026-08-03

fairydreaming merged 563dec81 into master 15 days ago

Reviewers

ggerganov

CISC

Assignees

No one assigned

Labels

None yet

Milestone

No milestone