From: Daniel Bevenius <redacted>
Date: Fri, 30 Jan 2026 10:12:53 +0000 (+0100)
Subject: convert : add missing return statement for GraniteMoeModel (#19202)
X-Git-Tag: upstream/0.0.8067~183
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=05625031547d95f7335abd012cad4cd07986819b;p=pkg%2Fggml%2Fsources%2Fllama.cpp

convert : add missing return statement for GraniteMoeModel (#19202)

This commit adds a missing return statement to the GraniteMoeModel class
to fix an issue in the model conversion process.

Resolves: https://github.com/ggml-org/llama.cpp/issues/19201
---

diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py
index a391717e3..eb43520f9 100755
--- a/convert_hf_to_gguf.py
+++ b/convert_hf_to_gguf.py
@@ -8806,6 +8806,7 @@ class GraniteMoeModel(GraniteModel):
             gate, up = data_torch.split(ffn_dim, dim=-2)
             yield from ModelBase.modify_tensors(self, gate, self.format_tensor_name(gguf.MODEL_TENSOR.FFN_GATE_EXP, bid), bid)
             yield from ModelBase.modify_tensors(self, up, self.format_tensor_name(gguf.MODEL_TENSOR.FFN_UP_EXP, bid), bid)
+            return
 
         has_experts = bool(self.hparams.get('num_local_experts'))