vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : add gguf_remove_key + remove split meta during quantize (#6591)

Browse source 
* 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 <z5269887@unsw.edu.au>
This commit is contained in:
jiez 2024-04-12 18:45:06 +08:00 • committed by GitHub
parent 5c4d767ac0
commit 91c736015b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 47 additions and 25 deletions
Download patch file Download diff file Expand all files Collapse all files

3
ggml.h
View file

@ -2289,6 +2289,9 @@ extern "C" {
GGML_API char * gguf_get_tensor_name (const struct gguf_context * ctx, int i);
GGML_API enum ggml_type gguf_get_tensor_type (const struct gguf_context * ctx, int i);
// removes key if it exists
GGML_API void gguf_remove_key(struct gguf_context * ctx, const char * key);
// overrides existing values or adds a new one
GGML_API void gguf_set_val_u8 (struct gguf_context * ctx, const char * key, uint8_t val);
GGML_API void gguf_set_val_i8 (struct gguf_context * ctx, const char * key, int8_t val);