[Model] Qwen3.5 dense and MoE support (no vision) (#19435)

* Unified delta net handling

* Remove old methods.

* Refactor and optimize

* Adapt autoregressive version from @ymcki

* Change to decay mask approach

* Fix bad permute

* Qwen 3.5 support

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Further fixes

* Use inheritance, remove unneeded conts

* Not like this!

* Remove ggml.h explicit import

* Remove transformers, fix the views

* ACTUALLY fix views, make super calls explicit in conversion.

* Fix conversion again

* Remove extra ggml.h imports

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Piotr Wilkin (ilintar)
2026-02-09 00:24:08 +01:00
committed by GitHub
parent e06088da0f
commit 39bf692af1
14 changed files with 1532 additions and 399 deletions
+3
View File
@@ -57,6 +57,7 @@ add_library(llama
models/deci.cpp
models/deepseek.cpp
models/deepseek2.cpp
models/delta.cpp
models/dots1.cpp
models/dream.cpp
models/ernie4-5-moe.cpp
@@ -122,6 +123,8 @@ add_library(llama
models/qwen3vl-moe.cpp
models/qwen3moe.cpp
models/qwen3next.cpp
models/qwen3-5.cpp
models/qwen3-5moe.cpp
models/refact.cpp
models/rnd1.cpp
models/rwkv6-base.cpp