mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-02 09:12:03 +00:00
rework, targeting llama-server
This commit is contained in:
@@ -20,6 +20,8 @@
|
||||
//
|
||||
struct llama_batch {
|
||||
int32_t n_tokens;
|
||||
int32_t max_tokens;
|
||||
bool is_view;
|
||||
|
||||
llama_token * token;
|
||||
float * embd;
|
||||
|
||||
Reference in New Issue
Block a user