diff --git a/common/speculative.cpp b/common/speculative.cpp
index 365372005cdc..e6ec8f6ac62f 100644
--- a/common/speculative.cpp
+++ b/common/speculative.cpp
@@ -1080,6 +1080,29 @@ struct common_speculative_impl_draft_dflash : public common_speculative_impl {
                     }
                 }
 
+                // sanitize non-finite feature values before fusing. on Metal, the
+                // mat-mat kernels stage f32 activations as f16 for the simdgroup
+                // multiply; Laguna's massive-activation rows (attention-sink tokens,
+                // |x| ~ 1e6 in the pre-final-norm residual) overflow f16 -> inf/nan.
+                // one poisoned row would otherwise NaN the whole drafter KV cache.
+                {
+                    size_t n_bad = 0;
+                    for (auto & v : features_buf) {
+                        if (!std::isfinite(v)) {
+                            v = v != v ? 0.0f : (v > 0.0f ? 65504.0f : -65504.0f);
+                            n_bad++;
+                        }
+                    }
+                    if (n_bad > 0) {
+                        static bool warned = false;
+                        if (!warned) {
+                            LOG_WRN("%s: sanitized %zu non-finite target feature values (f16 overflow on massive activations); "
+                                    "draft quality may degrade slightly on affected rows\n", __func__, n_bad);
+                            warned = true;
+                        }
+                    }
+                }
+
                 // fuse extracted features through DFlash encoder
                 llama_batch enc_batch = {
                     /*.n_tokens =*/ n_chunk,