happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

rpc : proper handling of data pointers to CPU buffers (#21030) 

The compute graph may contain tensors pointing to CPU buffers. In these
cases the buffer address is serialized as 0 and sent over the wire.
However, the data pointer is serialized as-is and this prevents proper
validation on the server side. This patches fixes this by serializing
the data pointer as 0 for non-RPC buffers and doing proper validation on
the server side.

closes: #21006
This commit is contained in:
Radoslav Gerganov 2026-03-27 10:59:35 +02:00 committed by GitHub
parent 37f230dd7c
commit ba38f3becc
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
ggml/src/ggml-rpc/ggml-rpc.cpp
View File

@ -589,8 +589,10 @@ static rpc_tensor serialize_tensor(const ggml_tensor * tensor) {
ggml_backend_buffer_t buffer = tensor->buffer;
ggml_backend_rpc_buffer_context * ctx = (ggml_backend_rpc_buffer_context *)buffer->context;
result.buffer = ctx != nullptr ? ctx->remote_ptr : 0;
result.data = reinterpret_cast<uint64_t>(tensor->data);
} else {
result.buffer = 0;
result.data = 0;
}
for (uint32_t i = 0; i < GGML_MAX_DIMS; i++) {
result.ne[i] = tensor->ne[i];
@ -606,7 +608,6 @@ static rpc_tensor serialize_tensor(const ggml_tensor * tensor) {
}
result.view_src = reinterpret_cast<uint64_t>(tensor->view_src);
result.view_offs = tensor->view_offs;
result.data = reinterpret_cast<uint64_t>(tensor->data);
// Avoid sending uninitialized data over the wire
memset(result.name, 0, sizeof(result.name));
@ -1443,9 +1444,11 @@ ggml_tensor * rpc_server::create_node(uint64_t id,
const rpc_tensor * tensor = it_ptr->second;
struct ggml_tensor * result = deserialize_tensor(ctx, tensor);
if (result == nullptr || result->buffer == nullptr) {
GGML_LOG_ERROR("[%s] invalid tensor: null %s (id=%" PRIu64 ")\n",
__func__, result == nullptr ? "tensor" : "buffer", id);
if (result == nullptr) {
return nullptr;
}
if (result->buffer == nullptr && result->data != nullptr) {
GGML_LOG_ERROR("[%s] invalid data ptr", __func__);
return nullptr;
}
tensor_map[id] = result;