mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-20 12:07:33 +00:00
graph : fix reuse check for recurrent inputs
This commit is contained in:
@@ -234,6 +234,10 @@ public:
|
||||
ggml_tensor * s_copy_extra; // I32 [n_rs - n_seqs]
|
||||
|
||||
const llama_memory_recurrent_context * mctx;
|
||||
|
||||
// used in view offsets, need to match for valid graph reuse
|
||||
uint32_t head;
|
||||
int32_t rs_z;
|
||||
};
|
||||
|
||||
class llm_graph_input_cross_embd : public llm_graph_input_i {
|
||||
|
||||
Reference in New Issue
Block a user