Skip to content

ggml-alloc: fix discrepency between measure&eval #2639

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 17, 2023
Merged

ggml-alloc: fix discrepency between measure&eval #2639

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 12 additions & 5 deletions ggml-alloc.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,10 +113,10 @@ void ggml_allocr_alloc(struct ggml_allocr * alloc, struct ggml_tensor * tensor)

size_t max_avail = 0;

// find the best fitting free block
// find the best fitting free block besides the last block
int best_fit_block = -1;
size_t best_fit_size = SIZE_MAX;
for (int i = 0; i < alloc->n_free_blocks; i++) {
for (int i = 0; i < alloc->n_free_blocks - 1; i++) {
struct free_block * block = &alloc->free_blocks[i];
max_avail = MAX(max_avail, block->size);
if (block->size >= size && block->size <= best_fit_size) {
Expand All @@ -128,10 +128,17 @@ void ggml_allocr_alloc(struct ggml_allocr * alloc, struct ggml_tensor * tensor)
AT_PRINTF("block %d\n", best_fit_block);

if (best_fit_block == -1) {
fprintf(stderr, "%s: not enough space in the buffer (needed %zu, largest block available %zu)\n",
__func__, size, max_avail);
GGML_ASSERT(!"not enough space in the buffer");
// the last block is our last resort
struct free_block * block = &alloc->free_blocks[alloc->n_free_blocks - 1];
if (block->size >= size) {
best_fit_block = alloc->n_free_blocks - 1;
max_avail = MAX(max_avail, block->size);
} else {
fprintf(stderr, "%s: not enough space in the buffer (needed %zu, largest block available %zu)\n",
__func__, size, max_avail);
GGML_ASSERT(!"not enough space in the buffer");
return;
}
}
struct free_block * block = &alloc->free_blocks[best_fit_block];
void * addr = block->addr;
Expand Down