mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-07-20 17:49:18 +00:00
context : add get_ctx_padding()
ggml-ci
This commit is contained in:
@ -84,8 +84,11 @@ struct llama_context {
|
||||
ggml_cgraph * graph,
|
||||
bool batched);
|
||||
|
||||
// max token position across all sequences in the current context
|
||||
llama_pos pos_max() const;
|
||||
|
||||
uint32_t get_ctx_padding(const llama_cparams & cparams) const;
|
||||
|
||||
void reset();
|
||||
|
||||
void prepare_k_shift();
|
||||
|
Reference in New Issue
Block a user