From c645b16990ad89e23ae77be6cd0f30ce95bc2cff Mon Sep 17 00:00:00 2001
From: Aman Gupta <amangupta052@gmail.com>
Date: Thu, 24 Sep 2026 02:02:53 +0800
Subject: [PATCH] fix v granularity

---
 src/llama-model.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index 402d0d4833..6fdde70ce0 100644
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -768,7 +768,7 @@ struct ggml_backend_meta_split_state llama_meta_device_get_split_state(const str
             }
             if (std::regex_match(tensor_name, pattern_attn_out_weight)) {
                 GGML_ASSERT(segments.size() == 1);
-                return {granularity_q};
+                return {granularity_head * hparams.n_embd_head_v(il)};
             }
             if (std::regex_match(tensor_name, pattern_attn_gate_weight)) {
                 GGML_ASSERT(segments.size() == 1);