mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-10-08 22:10:37 +02:00
RPC: add -sm tensor (#26610)
* rpc: allow -sm tensor * fix flush for apple rdma * move graph_uids to rpc_dispatcher * cont : fix conflict * cont: stop spinning dispatcher thread * remove meta backend change * add TODO to simplify logic * rpc: bump major version --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
co-authored by
Georgi Gerganov
parent
65840ed53c
commit
a46709b683
@@ -6,7 +6,7 @@
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
#define RPC_PROTO_MAJOR_VERSION 7
|
||||
#define RPC_PROTO_MAJOR_VERSION 8
|
||||
#define RPC_PROTO_MINOR_VERSION 0
|
||||
#define RPC_PROTO_PATCH_VERSION 0
|
||||
|
||||
|
||||
@@ -869,7 +869,12 @@ static struct ggml_backend_meta_split_state ggml_backend_meta_get_split_state(
|
||||
ggml_backend_meta_split_state split_state;
|
||||
switch (tensor->op) {
|
||||
case GGML_OP_NONE: {
|
||||
split_state = {GGML_BACKEND_SPLIT_AXIS_MIRRORED, {0}, {1}, 1};
|
||||
if (tensor->view_src != nullptr) {
|
||||
// full-tensor view created with ggml_view_tensor, transparent for the split state
|
||||
split_state = ggml_backend_meta_get_split_state(stc, tensor->view_src, assume_sync);
|
||||
} else {
|
||||
split_state = {GGML_BACKEND_SPLIT_AXIS_MIRRORED, {0}, {1}, 1};
|
||||
}
|
||||
} break;
|
||||
case GGML_OP_DUP: {
|
||||
split_state = handle_generic(src_ss, /*scalar_only =*/ true);
|
||||
|
||||
+748
-46
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user