Upgrade llama.cpp from b10319 to b10327

CLAUDE.md

@@ -6,7 +6,7 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 
 Java bindings for [llama.cpp](https://github.com/ggerganov/llama.cpp) via JNI, providing a high-level API for LLM inference in Java. The Java layer communicates with a native C++ library through JNI.
 
-Current llama.cpp pinned version: **b10319**
+Current llama.cpp pinned version: **b10327**
 
 ## Upgrading CUDA Version
 
@@ -429,7 +429,7 @@ needs no extra step here, `build-webui` re-reads the tag and rebuilds the matchi
 ships no UI):
 ```bash
 # needs node/npm + network; embed.cpp is plain C++17 (no npm)
-git clone --depth 1 --branch b10319 https://github.com/ggml-org/llama.cpp /tmp/lc
+git clone --depth 1 --branch b10327 https://github.com/ggml-org/llama.cpp /tmp/lc
 ( cd /tmp/lc/tools/ui && npm ci && npm run build \
   && ( cd dist && find . -type f -not -path './_gzip/*' \
        | while read -r f; do mkdir -p "_gzip/$(dirname "$f")"; gzip -9 -c "$f" > "_gzip/$f"; done ) \
@@ -469,7 +469,7 @@ cache lives in **Depot Cache** over sccache's **WebDAV** backend:
 - `SCCACHE_WEBDAV_TOKEN: ${{ secrets.DEPOT_TOKEN }}` — a Depot **organization** token, stored
   as the repo secret **`DEPOT_TOKEN`**.
 
-Because `sccache` is **content-addressed** and llama.cpp is pinned (`GIT_TAG b10319`), the
+Because `sccache` is **content-addressed** and llama.cpp is pinned (`GIT_TAG b10327`), the
 ~280 upstream object files are byte-identical every run, so a warm cache recompiles only the
 *changed* files. Depot's cache is **shared across all branches** (unlike GitHub's
 per-branch `actions/cache`), so every branch builds incrementally; a `b<nnnn>` version bump
@@ -1278,7 +1278,7 @@ ctest --test-dir build --output-on-failure -R "ResultsToJson"
 
 #### Upstream source location (in CMake build tree)
 
-llama.cpp is fetched via CMake FetchContent, pinned to `GIT_TAG b10319`.
+llama.cpp is fetched via CMake FetchContent, pinned to `GIT_TAG b10327`.
 
 **GoogleTest** is a separate `BUILD_TESTING`-only FetchContent (`GIT_TAG v1.17.0`), used solely
 by the `jllama_test` C++ unit-test binary — not by the shipped library, and not coupled to the

README.md

@@ -11,7 +11,7 @@
 **Build:**  
 ![Java 8+](https://img.shields.io/badge/Java-8%2B-informational)  
 ![Platform](https://img.shields.io/badge/Platform-Linux%20%7C%20macOS%20%7C%20Windows%20%7C%20Android-lightgrey)  
-[![llama.cpp b10319](https://img.shields.io/badge/llama.cpp-%23b10319-informational)](https://github.com/ggml-org/llama.cpp/releases/tag/b10319)  
+[![llama.cpp b10327](https://img.shields.io/badge/llama.cpp-%23b10327-informational)](https://github.com/ggml-org/llama.cpp/releases/tag/b10327)  
 [![JPMS](https://img.shields.io/badge/JPMS-modular%20JAR-25A162)](https://openjdk.org/projects/jigsaw/)  
 ![JUnit](https://img.shields.io/badge/tested%20with-JUnit6-25A162)  
 [![JSpecify](https://img.shields.io/badge/JSpecify-1.0.0%20%40NullMarked-25A162)](https://jspecify.dev)  

docs/history/llama-cpp-breaking-changes.md

@@ -579,3 +579,7 @@ Used during `llama.cpp` version bumps: when upgrading, scan this file from the r
 | b10313–b10318 | upstream verification (sandbox) | Remaining **6** patches re-verified against a clean b10318 checkout (ggml/llama.cpp commit `4cf5cab6`): fail-loud `PATCH_COMMAND` clean. **Configure-only verification per this step's process** (full build deferred to the b10319 final target). |
 | b10318–b10319 | `tools/mtmd/{clip-model.h,clip.cpp,mtmd-image.cpp}` (**vision-encoder (clip) image-token-limit preprocessing tweak — new `clip_hparams::set_limit_image_tokens()`**) | **No project-source change (final step of this b10310→b10319 follow-up walk).** Internal to the `clip` vision-encoder preprocessing path; not included directly by any project source file and unrelated to the Qwen3-TTS pipeline (`tts_engine.cpp` uses `mtmd_helper::gen_audio`/`mtmd_helper_bitmap_init_from_file`, not `clip`/`mtmd-image.cpp` directly). Zero diff under `common/`, `include/`, `tools/mtmd/mtmd.h`, `tools/mtmd/mtmd-helper.h`, `tools/server/*.h`, `tools/server/*.cpp`, `CMakeLists.txt`, `vendor/sheredom/subprocess.h`. |
 | b10318–b10319 | upstream verification (sandbox, final target) | Remaining **6** patches re-verified against a clean b10319 checkout (ggml/llama.cpp commit `4cb22cd5`): fail-loud `PATCH_COMMAND` clean. **Full local verification (mandatory for the final target):** fresh configure + full `cmake --build` (`libjllama.so` + `jllama_test` compile and link, `-O3`, no undefined references) + `ctest` **482/482 passing**. Closes the b10310→b10319 follow-up walk (3 steps: b10310→b10313→b10318→b10319). |
+| b10319–b10322 | `ggml/src/{ggml-metal/ggml-metal-ops.cpp,ggml-sycl/ssm_conv.cpp}` (**GPU backend internals**), `tools/ui/**` (**new chat-form @-mention picker feature, dominates the diff**) | **No project-source change.** Zero diff under `common/`, `include/`, `tools/mtmd/mtmd.h`, `tools/mtmd/mtmd-helper.h`, `tools/server/*.h`, `tools/server/*.cpp`, `CMakeLists.txt`, `vendor/sheredom/subprocess.h`. Only 3 commits; the bulk of the diff (1854/403 lines) is a new WebUI mention-picker feature (`ChatFormMentionPicker.svelte` + supporting hooks/utils), no C++ surface. |
+| b10319–b10322 | upstream verification (sandbox) | Remaining **6** patches re-verified against a clean b10322 checkout (ggml/llama.cpp commit `f8e30266`): fail-loud `PATCH_COMMAND` clean. **Configure-only verification per this step's process** (full build deferred to the b10327 final target). |
+| b10322–b10327 | `tools/tts/tts.cpp` (**reference-tool timing/logging tweak — now also reports vocoder time via `get_output`'s existing optional `out_n_samples` param**), `ggml/src/ggml-cuda/cpy.cu` (**GPU backend internal**), `tools/ui/**` (**large contenteditable chat-form rewrite, dominates the diff at 4950 lines**) | **No project-source change (final step of this b10319→b10327 walk).** `tools/mtmd/mtmd-helper.h` has **zero diff** across this whole range — confirmed via a direct diff of just that file. `mtmd_helper::gen_audio::get_output`'s 4th parameter (`int64_t * out_n_samples = nullptr`) already existed before this range; `tools/tts/tts.cpp` merely started passing it (for better timing logs), it did not become newly required. `tts_engine.cpp`'s existing 3-arg `gen.get_output(&sample_rate, &data, &data_len)` call stays valid unchanged. Zero diff under `common/`, `include/`, `tools/mtmd/mtmd.h`, `tools/server/*.h`, `tools/server/*.cpp`, `CMakeLists.txt`, `vendor/sheredom/subprocess.h`. |
+| b10322–b10327 | upstream verification (sandbox, final target) | Remaining **6** patches re-verified against a clean b10327 checkout (ggml/llama.cpp commit `69bf6437`): fail-loud `PATCH_COMMAND` clean. **Full local verification (mandatory for the final target):** fresh configure + full `cmake --build` (`libjllama.so` + `jllama_test` compile and link, `-O3`, no undefined references) + `ctest` **482/482 passing**. Closes the b10319→b10327 walk (2 steps: b10319→b10322→b10327), on a new branch (`claude/java-llama-cpp-b10327`) following on from the b10310→b10319 walk merged as PR #381. |

llama/CMakeLists.txt

@@ -173,7 +173,7 @@ set(LLAMA_BUILD_APP OFF CACHE BOOL "" FORCE)
 FetchContent_Declare(
 	llama.cpp
 	GIT_REPOSITORY https://github.com/ggerganov/llama.cpp.git
-	GIT_TAG        b10319
+	GIT_TAG        b10327
 	PATCH_COMMAND  ${CMAKE_COMMAND}
 		-DPATCH_DIR=${CMAKE_CURRENT_SOURCE_DIR}/patches
 		-DLLAMA_SRC=<SOURCE_DIR>

llama/src/main/java/net/ladenthin/llama/value/LlamaCppVersion.java

@@ -10,28 +10,28 @@
  * library was compiled against, exposed as a compile-time constant so callers can render a badge or
  * emit a startup log line without loading the native library.
  *
- * <p>{@link #LLAMA_CPP_VERSION} is a pure-Java string ({@code "b10319"}) that mirrors the
+ * <p>{@link #LLAMA_CPP_VERSION} is a pure-Java string ({@code "b10327"}) that mirrors the
  * {@code GIT_TAG} in {@code llama/CMakeLists.txt}. It is available even when {@code libjllama} is
  * absent (pure-Java checkout, before {@code System.load}), which is what makes it suitable for a
  * lightweight version badge in Android or other UIs.</p>
  *
  * <p>For the <em>authoritative</em> value that is baked into the native binary — the build number
- * plus the resolved upstream commit, e.g. {@code "b10319-<commit>"} — call
+ * plus the resolved upstream commit, e.g. {@code "b10327-<commit>"} — call
  * {@link net.ladenthin.llama.LlamaModel#getLlamaCppBuildInfo()} instead; that reads llama.cpp's own
  * {@code build-info} through JNI and therefore cannot drift from the compiled library (but requires
  * the native library to be loaded).</p>
  */
 public final class LlamaCppVersion {
 
     /**
-     * The pinned llama.cpp release tag this library was built against, e.g. {@code "b10319"}.
+     * The pinned llama.cpp release tag this library was built against, e.g. {@code "b10327"}.
      *
      * <p>Kept in lockstep with {@code GIT_TAG} in {@code llama/CMakeLists.txt} — see the
      * "Upgrading/Downgrading llama.cpp Version" checklist in {@code CLAUDE.md}. This is the
      * compile-time pin; use {@link net.ladenthin.llama.LlamaModel#getLlamaCppBuildInfo()} for the
      * value actually linked into the native binary.</p>
      */
-    public static final String LLAMA_CPP_VERSION = "b10319";
+    public static final String LLAMA_CPP_VERSION = "b10327";
 
     // Constants holder — not instantiable.
     private LlamaCppVersion() {}