Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.github/actions/windows-setup-cuda/action.yml
#	.github/workflows/release.yml
#	.github/workflows/server-sanitize.yml
#	models/templates/poolside-Laguna-S-2.1.jinja
#	scripts/sync_vendor.py
#	tests/test-backend-ops.cpp
#	tests/test-chat-auto-parser.cpp
#	tests/test-llama-archs.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/mtmd/CMakeLists.txt
#	tools/server/README.md

common/speculative.cpp

@@ -1032,7 +1032,14 @@ struct common_speculative_impl_draft_dflash : public common_speculative_impl {
             return true;
         }
 
-        if (batch_in.token == nullptr || batch_in.embd != nullptr) {
+        // Target prefill may contain token IDs or multimodal embeddings. Both
+        // produce the target-layer features used to seed the draft KV cache, so
+        // skipping the embedding batches leaves a hole in the draft's cache and
+        // the next injection fails to initialize.
+        // TODO: revisit after https://github.com/ggml-org/llama.cpp/pull/24669 is merged
+        const bool has_tokens     = batch_in.token != nullptr;
+        const bool has_embeddings = batch_in.embd  != nullptr;
+        if (has_tokens == has_embeddings) {
             return true;
         }