Skip to content

rpc : better caching of the base buffer pointer #11331

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

Merged
merged 1 commit into from
Jan 21, 2025
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 6 additions & 7 deletions ggml/src/ggml-rpc/ggml-rpc.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -181,7 +181,7 @@ struct ggml_backend_rpc_context {

struct ggml_backend_rpc_buffer_context {
std::shared_ptr<socket_t> sock;
std::unordered_map<ggml_backend_buffer_t, void *> base_cache;
void * base_ptr;
uint64_t remote_ptr;
};

Expand Down Expand Up @@ -423,16 +423,15 @@ static void ggml_backend_rpc_buffer_free_buffer(ggml_backend_buffer_t buffer) {

static void * ggml_backend_rpc_buffer_get_base(ggml_backend_buffer_t buffer) {
ggml_backend_rpc_buffer_context * ctx = (ggml_backend_rpc_buffer_context *)buffer->context;
if (ctx->base_cache.find(buffer) != ctx->base_cache.end()) {
return ctx->base_cache[buffer];
if (ctx->base_ptr != nullptr) {
return ctx->base_ptr;
}
rpc_msg_buffer_get_base_req request = {ctx->remote_ptr};
rpc_msg_buffer_get_base_rsp response;
bool status = send_rpc_cmd(ctx->sock, RPC_CMD_BUFFER_GET_BASE, &request, sizeof(request), &response, sizeof(response));
GGML_ASSERT(status);
void * base_ptr = reinterpret_cast<void *>(response.base_ptr);
ctx->base_cache[buffer] = base_ptr;
return base_ptr;
ctx->base_ptr = reinterpret_cast<void *>(response.base_ptr);
return ctx->base_ptr;
}

static rpc_tensor serialize_tensor(const ggml_tensor * tensor) {
Expand Down Expand Up @@ -557,7 +556,7 @@ static ggml_backend_buffer_t ggml_backend_rpc_buffer_type_alloc_buffer(ggml_back
if (response.remote_ptr != 0) {
ggml_backend_buffer_t buffer = ggml_backend_buffer_init(buft,
ggml_backend_rpc_buffer_interface,
new ggml_backend_rpc_buffer_context{sock, {}, response.remote_ptr},
new ggml_backend_rpc_buffer_context{sock, nullptr, response.remote_ptr},
response.remote_size);
return buffer;
} else {
Expand Down
Loading