sleepy/llama.cpp
1
0
Fork 0
Code Issues 16 Pull Requests Actions 36 Packages Projects Releases Wiki Activity

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

Browse Source 
* 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
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-context.cpp
+1 -1
View File
@@ -2013,7 +2013,7 @@ void llama_context::output_reorder() {
//
uint32_t llama_context::graph_max_nodes(uint32_t n_tokens) const {
if (model.arch == LLM_ARCH_QWEN3NEXT || model.arch == LLM_ARCH_KIMI_LINEAR) {
if (model.arch == LLM_ARCH_QWEN3NEXT || model.arch == LLM_ARCH_QWEN3_5 || model.arch == LLM_ARCH_QWEN3_5_MOE || model.arch == LLM_ARCH_KIMI_LINEAR) {
return std::max<uint32_t>(n_tokens * 40, 32u * model.n_tensors());
}
uint32_t res = std::max<uint32_t>(1024u, 8u*model.n_tensors());