Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Dflash support for nemotron-3.5 (#26905)

Browse Source 
* conversion: skip untrained DFlash embeddings

* Add Nemotron DFlash support

* Add DFlash NVFP4 support

* Address review comments

* add missing output_s for nvfp4

* Include change for keeping residual for last layer also if requested in future dflash models

* Update conversion/qwen.py

Defensive check, not needed

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

* Fixing bug introduced by merge conflict

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
This commit is contained in:
lnigam
2026-08-11 18:46:26 +05:30
committed by GitHub
co-authored by Sigbjørn Skjæret
parent 6e62ba5384
commit cc078b45b6
6 changed files with 42 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.h
+3 -2
View File
@@ -623,8 +623,9 @@ struct llama_model {
struct ggml_tensor * per_layer_model_proj = nullptr;
struct ggml_tensor * per_layer_proj_norm = nullptr;
// eagle3
struct ggml_tensor * fc = nullptr; // feature fusion layer
// eagle3 / dflash feature fusion layer
struct ggml_tensor * fc = nullptr;
struct ggml_tensor * fc_s = nullptr;
struct ggml_tensor * d2t = nullptr; // draft to target vocabulary mapping
// dspark