Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 13:28:50 +01:00
Code Issues Packages Projects Releases Wiki Activity

llama : fix memory leak in llama_batch_free (#5252)

Browse Source 
The llama_batch_init allocates memory for a fixed number of tokens.
However, the llama_batch_free only frees memory for the number of
tokens that were added to the batch.

This change-set uses a null terminated array for the batch seq_id, and
frees all the elements until the nullptr is reached. This change-set
also changes the name of the first parameter from `n_tokens` to
`n_tokens_alloc` to more clearly indicate that this value is the number
of tokens allocated to the batch, not the number of tokens in the batch.
This commit is contained in:
Ian Bull 2024-02-01 23:20:13 -08:00 committed by GitHub
parent 128dcbd3c9
commit e1e721094d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 11 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
llama.cpp
View File

@ -11377,22 +11377,24 @@ struct llama_batch llama_batch_get_one(
};
}
struct llama_batch llama_batch_init(int32_t n_tokens, int32_t embd, int32_t n_seq_max) {
struct llama_batch llama_batch_init(int32_t n_tokens_alloc, int32_t embd, int32_t n_seq_max) {
llama_batch batch = { 0, nullptr, nullptr, nullptr, nullptr, nullptr, nullptr, 0, 0, 0, };
if (embd) {
batch.embd = (float *) malloc(sizeof(float) * n_tokens * embd);
batch.embd = (float *) malloc(sizeof(float) * n_tokens_alloc * embd);
} else {
batch.token = (llama_token *) malloc(sizeof(llama_token) * n_tokens);
batch.token = (llama_token *) malloc(sizeof(llama_token) * n_tokens_alloc);
}
batch.pos = (llama_pos *) malloc(sizeof(llama_pos) * n_tokens);
batch.n_seq_id = (int32_t *) malloc(sizeof(int32_t) * n_tokens);
batch.seq_id = (llama_seq_id **) malloc(sizeof(llama_seq_id *) * n_tokens);
for (int i = 0; i < n_tokens; ++i) {
batch.pos = (llama_pos *) malloc(sizeof(llama_pos) * n_tokens_alloc);
batch.n_seq_id = (int32_t *) malloc(sizeof(int32_t) * n_tokens_alloc);
batch.seq_id = (llama_seq_id **) malloc(sizeof(llama_seq_id *) * (n_tokens_alloc + 1));
for (int i = 0; i < n_tokens_alloc; ++i) {
batch.seq_id[i] = (llama_seq_id *) malloc(sizeof(llama_seq_id) * n_seq_max);
}
batch.logits = (int8_t *) malloc(sizeof(int8_t) * n_tokens);
batch.seq_id[n_tokens_alloc] = nullptr;
batch.logits = (int8_t *) malloc(sizeof(int8_t) * n_tokens_alloc);
return batch;
}
@ -11403,7 +11405,7 @@ void llama_batch_free(struct llama_batch batch) {
if (batch.pos) free(batch.pos);
if (batch.n_seq_id) free(batch.n_seq_id);
if (batch.seq_id) {
for (int i = 0; i < batch.n_tokens; ++i) {
for (int i = 0; batch.seq_id[i] != nullptr; ++i) {
free(batch.seq_id[i]);
}
free(batch.seq_id);