ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

rpc : fix segfault with nkvo (#9389)

Browse source 
* rpc : fix nkvo

* rpc : buf_size must not be static

ref: #9337

---------

Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
Radoslav Gerganov 2024-09-09 18:40:10 +03:00 • committed by GitHub
parent 5fac4d5764
commit 293bebe077
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 16 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

6
ggml/src/ggml-cuda.cu
View file

@ -2552,7 +2552,11 @@ GGML_CALL static enum ggml_status ggml_backend_cuda_graph_compute(ggml_backend_t
for (int i = 0; i < cgraph->n_nodes; i++) {
ggml_tensor * node = cgraph->nodes[i];
if (node->src[0] && ggml_backend_buffer_is_cuda_split(node->src[0]->buffer)) {
if (ggml_is_empty(node) || node->op == GGML_OP_RESHAPE || node->op == GGML_OP_TRANSPOSE || node->op == GGML_OP_VIEW || node->op == GGML_OP_PERMUTE || node->op == GGML_OP_NONE) {
continue;
}
if (node->src[0] && node->src[0]->buffer && ggml_backend_buffer_is_cuda_split(node->src[0]->buffer)) {
use_cuda_graph = false; // Split buffers are not supported by CUDA graph capture
#ifndef NDEBUG
GGML_CUDA_LOG_WARN("%s: disabling CUDA graphs due to split buffer\n", __func__);