mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-08-18 14:18:50 -04:00
memory : handle kv_unified for hybrid models (#15050)
This commit is contained in:
@@ -39,6 +39,7 @@ public:
|
||||
/* common */
|
||||
uint32_t n_seq_max,
|
||||
bool offload,
|
||||
bool unified,
|
||||
/* layer filters */
|
||||
layer_filter_cb && filter_attn = nullptr,
|
||||
layer_filter_cb && filter_recr = nullptr);
|
||||
|
Reference in New Issue
Block a user