vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

sync : ggml (#6351)

Browse source 
* sync : ggml

ggml-ci

* cuda : move GGML_CUDA_DMMV constants to dmmv.cuh

---------

Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
Georgi Gerganov 2024-03-29 17:45:46 +02:00 • committed by GitHub
parent 069574775c
commit d48ccf3ad4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 25 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

9
ggml-alloc.c
View file

@ -705,8 +705,13 @@ 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