nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 22 Packages Projects Releases Wiki Activity

llama : add support for Nemotron 3 Super (#20411)

Browse Source 
* llama : add support for Nemotron 3 Super

This commit adds support for the Nemotron 3 Super model (120B.A12B)
enabling this model to be converted to GGUF format and run in llama.cpp.

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Matt Clayton <156335168+mattjcly@users.noreply.github.com>
This commit is contained in:
Daniel Bevenius
2026-03-11 19:27:53 +01:00
committed by GitHub
co-authored by Georgi Gerganov Matt Clayton
parent 76ea1c1c46
commit eaf1d7930c
11 changed files with 97 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
gguf-py/gguf/gguf_writer.py
+3
View File
@@ -859,6 +859,9 @@ class GGUFWriter:
def add_moe_every_n_layers(self, value: int) -> None:
self.add_uint32(Keys.LLM.MOE_EVERY_N_LAYERS.format(arch=self.arch), value)
def add_moe_latent_size(self, value: int) -> None:
self.add_uint32(Keys.LLM.MOE_LATENT_SIZE.format(arch=self.arch), value)
def add_nextn_predict_layers(self, count: int) -> None:
self.add_uint32(Keys.LLM.NEXTN_PREDICT_LAYERS.format(arch=self.arch), count)