feat: support packed INT4 convrot models (#2276)

Co-authored-by: noctrex <noctrex@gmail.com>
This commit is contained in:
leejetandnoctrex authored and GitHub committed 2026-11-06 00:35:58 +08:00
1 parent 58bb3c1b1c
commit 7952693004
48 files changed
+2003 -102

No files matched your search

+1 -1
View File
@@ -319,7 +319,7 @@ protected:
tensor_storage_map.find(prefix + "to_k_ip.weight") != tensor_storage_map.end()) {
has_ip = true;
int64_t inner_dim = d_head * n_head;
int64_t ip_dim = tensor_storage_map.at(prefix + "to_k_ip.weight").ne[0];
int64_t ip_dim = tensor_storage_map.at(prefix + "to_k_ip.weight").logical_ne0();
blocks["to_k_ip"] = std::shared_ptr<GGMLBlock>(new Linear(ip_dim, inner_dim, false));
blocks["to_v_ip"] = std::shared_ptr<GGMLBlock>(new Linear(ip_dim, inner_dim, false));
}