llama.cpp
Remove split metadata when quantize model shards
#6591
Merged

Remove split metadata when quantize model shards #6591

zj040045
Remove split metadata when quantize model shards
502d069b
slaren
slaren commented on 2024-04-10
slaren
slaren commented on 2024-04-10
phymbert
phymbert requested changes on 2024-04-10
github-actions
phymbert
Find metadata key by enum
29ed5d60
Correct loop range for gguf_remove_key and code format
ad0710aa
Free kv memory
fa908c08
slaren
slaren approved these changes on 2024-04-12
phymbert
phymbert approved these changes on 2024-04-12
ggerganov
ggerganov approved these changes on 2024-04-12
ggerganov ggerganov merged 91c73601 into master 1 year ago
zj040045
phymbert

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone