Early return for zero size calls to get_tensor. (llama/5482)

* Early return for zero size calls to get_tensor. Signed-off-by: Adam Treat <[email protected]> * Update ggml-kompute.cpp Co-authored-by: Georgi Gerganov <[email protected]> * Update ggml-kompute.cpp Co-authored-by: Georgi Gerganov <[email protected]> * Add an early return to the get/set tensor when the size is null. Signed-off-by: Adam Treat <[email protected]> * Early return after the assertions. Signed-off-by: Adam Treat <[email protected]> * Since we do the early return in the generic backend now no reason to do so here as well. Signed-off-by: Adam Treat <[email protected]> --------- Signed-off-by: Adam Treat <[email protected]> Co-authored-by: Georgi Gerganov <[email protected]>
ggerganov · Feb 19, 2024 · f91c377 · f91c377
1 parent c58fecf
commit f91c377
Showing 1 changed file with 8 additions and 0 deletions.
diff --git a/src/ggml-backend.c b/src/ggml-backend.c
@@ -219,6 +219,10 @@ GGML_CALL void ggml_backend_tensor_set(struct ggml_tensor * tensor, const void *
  GGML_ASSERT(buf != NULL && "tensor buffer not set");
  GGML_ASSERT(offset + size <= ggml_nbytes(tensor) && "tensor write out of bounds");
 
+ if (!size) {
+ return;
+ }
+
  tensor->buffer->iface.set_tensor(buf, tensor, data, offset, size);
 }
 
@@ -229,6 +233,10 @@ GGML_CALL void ggml_backend_tensor_get(const struct ggml_tensor * tensor, void *
  GGML_ASSERT(tensor->buffer != NULL && "tensor buffer not set");
  GGML_ASSERT(offset + size <= ggml_nbytes(tensor) && "tensor read out of bounds");
 
+ if (!size) {
+ return;
+ }
+
  tensor->buffer->iface.get_tensor(buf, tensor, data, offset, size);
 }