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

context : add get_ctx_padding()

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2025-01-17 11:51:35 +02:00
parent b4ec1d4429
commit f0713498fd
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
3 changed files with 10 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
src/llama-context.h
View file

@ -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();