root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 10:54:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

train-text-from-scratch : fix assert failure in ggml-alloc (#3618)

Browse Source
This commit is contained in:
slaren 2023-10-17 19:00:58 +02:00 committed by GitHub
parent e74c705e15
commit a5e8c1d8c7
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 9 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
examples/train-text-from-scratch/train-text-from-scratch.cpp
View File

@ -253,13 +253,14 @@ static void init_model(struct my_llama_model * model) {
set_param_model(model);
// measure data size
struct ggml_allocr * alloc = NULL;
alloc = ggml_allocr_new_measure(tensor_alignment);
alloc_model(alloc, model);
size_t size = 0;
for (struct ggml_tensor * t = ggml_get_first_tensor(ctx); t != NULL; t = ggml_get_next_tensor(ctx, t)) {
size += GGML_PAD(ggml_nbytes(t), tensor_alignment);
}
// allocate data
model->data.resize(ggml_allocr_max_size(alloc) + tensor_alignment);
ggml_allocr_free(alloc);
struct ggml_allocr * alloc = NULL;
model->data.resize(size + tensor_alignment);
alloc = ggml_allocr_new(model->data.data(), model->data.size(), tensor_alignment);
alloc_model(alloc, model);
ggml_allocr_free(alloc);
@ -1094,11 +1095,9 @@ int main(int argc, char ** argv) {
struct ggml_tensor * target_probs = ggml_new_tensor_3d(ctx_input, GGML_TYPE_F32, n_vocab, n_tokens, n_batch);
// measure required memory for input tensors
alloc = ggml_allocr_new_measure(tensor_alignment);
ggml_allocr_alloc(alloc, tokens_input);
ggml_allocr_alloc(alloc, target_probs);
size_t max_input_size = ggml_allocr_max_size(alloc) + tensor_alignment;
ggml_allocr_free(alloc);
size_t max_input_size = GGML_PAD(ggml_nbytes(tokens_input), tensor_alignment) +
GGML_PAD(ggml_nbytes(target_probs), tensor_alignment) +
tensor_alignment;
printf("%s: input_size = %zu bytes (%.1f MB)\n", __func__, max_input_size, (float) max_input_size / (1024.0f*1024.0f));
// allocate input tensors