fix: gate turbo V unpad on V type, not K type

Author: TheTom

src/llama-graph.cpp

@@ -2189,7 +2189,8 @@ ggml_tensor * llm_graph_context::build_attn(
 
     // TurboQuant: if V was padded, the output has padded dimensions.
     // Extract original V head_dim after inverse WHT (applied inside build_attn_mha).
-    if (k->type == GGML_TYPE_TURBO3_0 || k->type == GGML_TYPE_TURBO4_0 || k->type == GGML_TYPE_TURBO2_0) {
+    // NOTE: gate on v->type (not k->type) for asymmetric configs where K=q8_0 but V=turbo
+    if (v->type == GGML_TYPE_TURBO3_0 || v->type == GGML_TYPE_TURBO4_0 || v->type == GGML_TYPE_TURBO2_0) {
         const int64_t orig_v_head = hparams.n_embd_head_v(il);
         // cur is 2D: (n_embd_head * n_head, n_tokens) after build_attn_mha
         const int64_t padded_v_head = v->ne[0];
@@ -2415,7 +2416,8 @@ ggml_tensor * llm_graph_context::build_attn(
     cb(cur, "kqv_out", il);
 
     // TurboQuant: if V was padded, extract original V head_dim after inverse WHT
-    if (k->type == GGML_TYPE_TURBO3_0 || k->type == GGML_TYPE_TURBO4_0 || k->type == GGML_TYPE_TURBO2_0) {
+    // NOTE: gate on v->type (not k->type) for asymmetric configs where K=q8_0 but V=turbo
+    if (v->type == GGML_TYPE_TURBO3_0 || v->type == GGML_TYPE_TURBO4_0 || v->type == GGML_TYPE_TURBO2_0) {
         const int64_t orig_v_head = hparams.n_embd_head_v(il);
         const int64_t padded_v_head = v->ne[0];
         if (padded_v_head != orig_v_head) {