talk-llama : sync llama.cpp

This commit is contained in:
Georgi Gerganov
2025-07-28 10:09:47 +03:00
parent 5b4646df1a
commit d0a9d8c7f8
27 changed files with 3566 additions and 995 deletions

View File

@ -11,8 +11,8 @@ struct llama_cparams {
uint32_t n_batch;
uint32_t n_ubatch;
uint32_t n_seq_max;
int n_threads; // number of threads to use for generation
int n_threads_batch; // number of threads to use for batch processing
int32_t n_threads; // number of threads to use for generation
int32_t n_threads_batch; // number of threads to use for batch processing
float rope_freq_base;
float rope_freq_scale;
@ -33,6 +33,7 @@ struct llama_cparams {
bool no_perf;
bool warmup;
bool op_offload;
bool kv_unified;
enum llama_pooling_type pooling_type;