Merge commit '9d5d882d8cd0f0a9283d87ed5e6fe3ee0d925fb1' into concedo_experimental

# Conflicts:
#	.github/labeler.yml
#	app/CMakeLists.txt
#	app/llama.cpp
#	build-xcframework.sh
#	common/CMakeLists.txt
#	common/download.h
#	docs/backend/SYCL.md
#	docs/backend/snapdragon/CMakeUserPresets.json
#	docs/speculative.md
#	ggml/CMakeLists.txt
#	ggml/include/ggml-sycl.h
#	ggml/src/ggml-hexagon/CMakeLists.txt
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/cmake-toolchain.cmake
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/hex-dma.h
#	ggml/src/ggml-hexagon/htp/hex-utils.h
#	ggml/src/ggml-hexagon/htp/hmx-flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/htp_iface.idl
#	ggml/src/ggml-hexagon/htp/hvx-base.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/libggml-htp.inf
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/norm.cl
#	ggml/src/ggml-sycl/conv3d.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	scripts/snapdragon/adb/run-completion.sh
#	scripts/snapdragon/adb/run-tool.sh
#	scripts/snapdragon/ggml-hexagon-profile.py
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-thread-safety.cpp
#	tools/llama-bench/llama-bench.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/mtmd/tests/test-deepseek-ocr.py

src/llama-model.cpp

@@ -836,6 +836,7 @@ const char * llm_type_name(llm_type type) {
         case LLM_TYPE_160M:          return "160M";
         case LLM_TYPE_190M:          return "190M";
         case LLM_TYPE_220M:          return "220M";
+        case LLM_TYPE_230M:          return "230M";
         case LLM_TYPE_250M:          return "250M";
         case LLM_TYPE_256M:          return "256M";
         case LLM_TYPE_270M:          return "270M";

src/llama-model.h

@@ -36,6 +36,7 @@ enum llm_type {
     LLM_TYPE_160M,
     LLM_TYPE_190M,
     LLM_TYPE_220M,
+    LLM_TYPE_230M,
     LLM_TYPE_250M,
     LLM_TYPE_256M,
     LLM_TYPE_270M,

src/llama-quant.cpp

@@ -849,7 +849,7 @@ static void init_quantize_state_counters(quantize_state_impl & qs, std::vector<t
             qs.has_tied_embeddings = false;
         }
     }
-    qs.n_ffn_down = qs.n_ffn_gate = qs.n_ffn_up = (int)qs.model.hparams.n_layer();
+    qs.n_ffn_down = qs.n_ffn_gate = qs.n_ffn_up = (int)qs.model.hparams.n_layer_all;
 }
 
 //

src/models/lfm2.cpp

@@ -13,6 +13,7 @@ void llama_model_lfm2::load_arch_hparams(llama_model_loader & ml) {
     hparams.n_layer_dense_lead = hparams.n_layer();
 
     switch (hparams.n_ff()) {
+        case  2560: type = LLM_TYPE_230M; break;
         case  4608: type = LLM_TYPE_350M; break;
         case  6912: type = LLM_TYPE_700M; break;
         case  8192: type = LLM_TYPE_1_2B; break;