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

Update llama.cpp

Browse source 
Add review comments

Co-authored-by: Pavol Rusnak <pavol@rusnak.io>
This commit is contained in:
Christian Falch 2023-04-01 18:46:14 +02:00 • committed by GitHub
parent 14804b7978
commit a0c895c087
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama.cpp
View file

@ -1670,7 +1670,7 @@ int llama_model_quantize(
// Returns the KV cache that will contain the context for the // Returns the KV cache that will contain the context for the
// ongoing prediction with the model. // ongoing prediction with the model.
uint8_t* llama_get_kv_cache(struct llama_context * ctx) { const uint8_t * llama_get_kv_cache(struct llama_context * ctx) {
return ctx->model.kv_self.buf.data(); return ctx->model.kv_self.buf.data();
} }