]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
llama : add gguf_remove_key + remove split meta during quantize (llama/6591)
authorjiez <redacted>
Fri, 12 Apr 2024 10:45:06 +0000 (18:45 +0800)
committerGeorgi Gerganov <redacted>
Sat, 11 May 2024 18:30:08 +0000 (21:30 +0300)
commit5576fa5fd03a9eb70feab09509675ba4123e2bb4
tree8d43f793e746c222deed1c6cc31885a421dcb97f
parent8cd3975bf21657c6d1e80c7c61830977b962539e
llama : add gguf_remove_key + remove split meta during quantize (llama/6591)

* Remove split metadata when quantize model shards

* Find metadata key by enum

* Correct loop range for gguf_remove_key and code format

* Free kv memory

---------

Co-authored-by: z5269887 <redacted>
include/ggml/ggml.h
src/ggml.c