tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-18 05:56:00 -04:00
Code Issues Packages Projects Releases Wiki Activity

llama : deprecate llama_kv_self_ API (#14030)

Browse Source 
* llama : deprecate llama_kv_self_ API

ggml-ci

* llama : allow llama_memory_(nullptr)

ggml-ci

* memory : add flag for optional data clear in llama_memory_clear

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-06 14:11:15 +03:00
committed by GitHub
parent 487a5e0401
commit 745aa5319b
34 changed files with 206 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/simple-chat/simple-chat.cpp
View File

@@ -98,7 +98,7 @@ int main(int argc, char ** argv) {
auto generate = [&](const std::string & prompt) {
std::string response;
const bool is_first = llama_kv_self_seq_pos_max(ctx, 0) == 0;
const bool is_first = llama_memory_seq_pos_max(llama_get_memory(ctx), 0) == 0;
// tokenize the prompt
const int n_prompt_tokens = -llama_tokenize(vocab, prompt.c_str(), prompt.size(), NULL, 0, is_first, true);
@@ -113,7 +113,7 @@ int main(int argc, char ** argv) {
while (true) {
// check if we have enough space in the context to evaluate this batch
int n_ctx = llama_n_ctx(ctx);
int n_ctx_used = llama_kv_self_seq_pos_max(ctx, 0);
int n_ctx_used = llama_memory_seq_pos_max(llama_get_memory(ctx), 0);
if (n_ctx_used + batch.n_tokens > n_ctx) {
printf("\033[0m\n");
fprintf(stderr, "context size exceeded\n");