ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

Browse source 
* llama : refactor llama_context, llama_kv_cache, llm_build_context

ggml-ci

* graph : don't mutate the KV cache during defrag

ggml-ci

* context : reduce virtuals + remove test function

ggml-ci

* context : move interface implementation to source file + factory

ggml-ci

* graph : move KV cache build functions to llama_context impl

ggml-ci

* graph : remove model reference from build_pooling

ggml-ci

* graph : remove llama_model reference

ggml-ci

* kv_cache : provide rope factors

ggml-ci

* graph : rework inputs to use only unique_ptr, remove attn input abstraction

ggml-ci

* context : remove llama_context_i abstraction

ggml-ci

* context : clean-up

ggml-ci

* graph : clean-up

ggml-ci

* llama : remove redundant keywords (struct, enum)

ggml-ci

* model : adapt gemma3

ggml-ci

* graph : restore same attention ops as on master

ggml-ci

* llama : remove TODO + fix indent

ggml-ci
This commit is contained in:
Georgi Gerganov 2025-03-13 12:35:44 +02:00 • committed by GitHub
parent 2048b5913d
commit e0dbec0bc6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
46 changed files with 13903 additions and 12190 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_get_kv_cache_used_cells(ctx) == 0;
const bool is_first = llama_kv_self_used_cells(ctx) == 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_get_kv_cache_used_cells(ctx);
int n_ctx_used = llama_kv_self_used_cells(ctx);
if (n_ctx_used + batch.n_tokens > n_ctx) {
printf("\033[0m\n");
fprintf(stderr, "context size exceeded\n");