talk-llama : sync llama.cpp

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-05-27 17:08:24 +03:00
parent 546928c33f
commit 26eb48cb08
18 changed files with 1968 additions and 1178 deletions

View File

@ -4,6 +4,8 @@
#include <cstdint>
#define LLAMA_MAX_PARALLEL_SEQUENCES 64
struct llama_cparams {
uint32_t n_ctx; // context size used during inference
uint32_t n_batch;