From: Daniel Bevenius <redacted>
Date: Wed, 21 Jan 2026 17:31:34 +0000 (+0100)
Subject: llama : clarify nemotron-h.cpp comment about RoPE [no ci] (#18997)
X-Git-Tag: upstream/0.0.8067~271
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=9da3dcd75313b4c492b1b3b0e189ecc70906a195;p=pkg%2Fggml%2Fsources%2Fllama.cpp

llama : clarify nemotron-h.cpp comment about RoPE [no ci] (#18997)

This commit removes the mention of RoPE in the comment for the Q and K
computation as RoPE is not applied.
---

diff --git a/src/models/nemotron-h.cpp b/src/models/nemotron-h.cpp
index eb135e63f..079c730ac 100644
--- a/src/models/nemotron-h.cpp
+++ b/src/models/nemotron-h.cpp
@@ -67,7 +67,7 @@ ggml_tensor * llm_build_nemotron_h::build_attention_layer(ggml_tensor *
                                                           const llama_model &       model,
                                                           const int64_t             n_embd_head,
                                                           const int                 il) {
-    // compute Q and K and (optionally) RoPE them
+    // compute Q and K
     ggml_tensor * Qcur = build_lora_mm(model.layers[il].wq, cur);
     cb(Qcur, "Qcur", il);
     if (model.layers[il].bq) {