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

rpc : buf_size must not be static

Browse source 
ref: #9337
This commit is contained in:
Radoslav Gerganov 2024-09-09 16:57:47 +03:00
parent 6e801df136
commit 8f5f25cd72
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml/src/ggml-rpc.cpp
View file

@ -1062,7 +1062,7 @@ bool rpc_server::graph_compute(const std::vector<uint8_t> & input, std::vector<u
const rpc_tensor * tensors = (const rpc_tensor *)(input.data() + sizeof(n_nodes) + n_nodes*sizeof(uint64_t) + sizeof(n_tensors)); const rpc_tensor * tensors = (const rpc_tensor *)(input.data() + sizeof(n_nodes) + n_nodes*sizeof(uint64_t) + sizeof(n_tensors));
GGML_PRINT_DEBUG("[%s] n_nodes: %u, n_tensors: %u\n", __func__, n_nodes, n_tensors); GGML_PRINT_DEBUG("[%s] n_nodes: %u, n_tensors: %u\n", __func__, n_nodes, n_tensors);
static size_t buf_size = ggml_tensor_overhead()*(n_nodes*20 + n_tensors) + ggml_graph_overhead_custom(n_nodes, false); size_t buf_size = ggml_tensor_overhead()*(n_nodes + n_tensors) + ggml_graph_overhead_custom(n_nodes, false);
struct ggml_init_params params = { struct ggml_init_params params = {
/*.mem_size =*/ buf_size, /*.mem_size =*/ buf_size,
/*.mem_buffer =*/ NULL, /*.mem_buffer =*/ NULL,