models : support qwen3.5 series (#19468)

* support qwen3.5 series * remove deepstack for now, and some code clean * code clean * add FULL_ATTENTION_INTERVAL metadata * code clean * reorder v heads for linear attention to avoid expensive interleaved repeat
2026-02-11 00:00:26 +08:00
parent 9a96352729
commit fc0fe40049
17 changed files with 2096 additions and 10 deletions
@@ -122,6 +122,8 @@ add_library(llama
            models/qwen3vl-moe.cpp
            models/qwen3moe.cpp
            models/qwen3next.cpp
+            models/qwen35.cpp
+            models/qwen35moe.cpp
            models/refact.cpp
            models/rnd1.cpp
            models/rwkv6-base.cpp