CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

move to llama_batch_ext

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-02-16 00:02:53 +01:00
parent f2e59a8eb9
commit 17d3658b5f
8 changed files with 222 additions and 117 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
common/common.cpp
View File

@@ -1610,20 +1610,29 @@ std::pair<std::string, std::string> common_get_hf_file(const std::string &, cons
// Batch utils
//
void common_batch_clear(struct llama_batch * batch) {
llama_batch_clear(batch);
// DEPRECATED
void common_batch_clear(struct llama_batch & batch) {
batch.n_tokens = 0;
}
// DEPRECATED
void common_batch_add(
struct llama_batch * batch,
struct llama_batch & batch,
llama_token id,
llama_pos pos,
const std::vector<llama_seq_id> & seq_ids,
bool logits) {
int32_t res = llama_batch_add_text_token(batch, id, pos, seq_ids.data(), seq_ids.size(), logits);
if (res == -1) {
LOG_ERR("%s: llama_batch size exceeded\n", __func__);
GGML_ASSERT(batch.seq_id[batch.n_tokens] && "llama_batch size exceeded");
batch.token [batch.n_tokens] = id;
batch.pos [batch.n_tokens] = pos;
batch.n_seq_id[batch.n_tokens] = seq_ids.size();
for (size_t i = 0; i < seq_ids.size(); ++i) {
batch.seq_id[batch.n_tokens][i] = seq_ids[i];
}
batch.logits [batch.n_tokens] = logits;
batch.n_tokens++;
}
//