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.
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
whisper : allocate encoder results in dedicated buffer #1964
Conversation
// TODO: this still triggers the assert: | ||
//struct ggml_tensor * cur = ggml_view_tensor(ctx0, wstate.embd_conv); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
With the wstate.embd_conv
now pre-allocated, this view still triggers the assert:
Assertion failed: (tensor_alloc->offset == SIZE_MAX), function ggml_gallocr_init_tensor, file ggml-alloc.c, line 739.
Not sure why
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The code that stores the allocation location of leafs didn't take into account pre-allocated leafs. This should fix it:
diff --git a/ggml-alloc.c b/ggml-alloc.c
index 8ac1d3e..60b86c2 100644
--- a/ggml-alloc.c
+++ b/ggml-alloc.c
@@ -701,8 +701,13 @@ bool ggml_gallocr_reserve_n(ggml_gallocr_t galloc, struct ggml_cgraph * graph, c
struct ggml_tensor * leaf = graph->leafs[i];
struct hash_node * hn = ggml_gallocr_hash_get(galloc, leaf);
galloc->leaf_allocs[i].buffer_id = hn->buffer_id;
- galloc->leaf_allocs[i].leaf.offset = hn->offset;
- galloc->leaf_allocs[i].leaf.size_max = ggml_backend_buft_get_alloc_size(galloc->bufts[hn->buffer_id], leaf);
+ if (leaf->view_src || leaf->data) {
+ galloc->leaf_allocs[i].leaf.offset = SIZE_MAX;
+ galloc->leaf_allocs[i].leaf.size_max = 0;
+ } else {
+ galloc->leaf_allocs[i].leaf.offset = hn->offset;
+ galloc->leaf_allocs[i].leaf.size_max = ggml_backend_buft_get_alloc_size(galloc->bufts[hn->buffer_id], leaf);
+ }
}
// reallocate buffers if needed
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
With just this change applied on master
the code also works (i.e. without pre-allocating the tensors). But if I understand correctly, it is technically not correct because nothing guarantees that the data in these tensors would not be overwritten by some ops. Since they are currently at the end of the computation graphs it seems to produce correct results, but the concern is that this is not very future-proof if we expand the graphs in the future - is that correct?
What if I use ggml_set_output(ctx0, wstate.embd_conv);
in whisper_build_graph_conv()
to guarantee that the data would not be overwritten?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yes, with ggml_set_output
it would guarantee that the tensor is never overwritten.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Would pre-allocating the tensors as proposed in this PR have any advantage over the ggml_set_output
option? Since with this PR we now have to perform extra copy of the data between the graph calls, which otherwise is not needed.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I don't think there would be any significant advantage. Maybe it would allow using ggml_gallocr_reserve
here instead of ggml_gallocr_alloc_graph
, but the difference would be minimal:
Lines 496 to 502 in 66df44b
// since there are dependencies between the different graphs, | |
// we need to allocate them instead of only reserving to get the correct compute buffer size | |
if (!ggml_gallocr_alloc_graph(alloc, get_graph())) { | |
// failed to allocate the compute buffer | |
WHISPER_LOG_ERROR("%s: failed to allocate the compute buffer\n", __func__); | |
return false; | |
} |
Picked the |
fix #1959
Allocate the encoder results tensors (
embd_conv
andembd_enc
) in dedicated backend buffer. Copy the results into these tensors and used them in follow-up graphs