bernardladenthin · bernardladenthin · Sep 28, 2026 · Sep 28, 2026
@@ -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: **b11222**
+Current llama.cpp pinned version: **b11236**
 
 ## Upgrading CUDA Version
 
@@ -538,7 +538,7 @@ needs no extra step here, `build-webui` re-reads the tag and rebuilds the matchi
 ships no UI):
 ```bash
 # needs node/npm + network for the asset build; the embed step is plain cmake -P
-git clone --depth 1 --branch b11222 https://github.com/ggml-org/llama.cpp /tmp/lc
+git clone --depth 1 --branch b11236 https://github.com/ggml-org/llama.cpp /tmp/lc
 ( cd /tmp/lc/tools/ui && npm ci && npm run build )
 mkdir -p webui-generated /tmp/ui-gen
 cmake -DUI_SOURCE_DIR=/tmp/lc/tools/ui -DUI_BINARY_DIR=/tmp/ui-gen \
@@ -578,7 +578,7 @@ 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 b11222`), the
+Because `sccache` is **content-addressed** and llama.cpp is pinned (`GIT_TAG b11236`), 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
@@ -776,7 +776,7 @@ Current patches:
 
 | Patch | Fixes |
 |-------|-------|
-| `0001-win32-arg-parse-embed-guard.patch` | Windows JNI regression from llama.cpp **#24779** (introduced b9739): on Windows `common_params_parse` re-derived argv from the **process** command line (`GetCommandLineW`) and adopted it, so an embedded/JNI caller (`java.exe`) lost its `--model …` args → "Failed to parse model parameters". b9789 narrowed the unconditional override to a **count-guard** (`if (static_cast<int>(utf8.buf.size()) == argc) { argv = utf8.ptrs.data(); }`), but that is exactly the variant the project already found breaks its Windows server-integration tests (when the embedded argv length coincides with `java.exe`'s). The patch carries the **complete upstream change** (so it can be submitted to llama.cpp verbatim and then dropped here): **(1)** `common_params_parse` parses **exactly the argv it is given** (no `GetCommandLineW` magic) and a new `common_params_parse_main()` wrapper holds the UTF-8 recovery for the standalone tools' `main()` (`common/arg.{cpp,h}`); **(2)** the **~34 standalone `main()` call sites** (every `common_params_parse(argc, argv, …)` across `tools/*`, `examples/*` and the `tests/*` programs) flip to `common_params_parse_main()`; **(3)** a `tests/test-arg-parser.cpp` regression case pins that `common_params_parse` honors a caller-supplied argv. The embedded caller (`jllama.cpp`) keeps calling `common_params_parse` and is never overridden. **Our subproject build compiles only the `arg.{cpp,h}` core** — `LLAMA_BUILD_TOOLS`/`LLAMA_BUILD_TESTS` are OFF for a FetchContent subproject — so the flips + test are applied-but-not-compiled here; they were validated via a one-off `-DLLAMA_BUILD_TOOLS=ON -DLLAMA_BUILD_TESTS=ON` build (the new test compiles and its asserts pass; `test-arg-parser`'s only red there is the live `ggml.ai` download check, which is sandbox-network, not the patch). Because it spans **36 files** it must be refreshed on every llama.cpp bump (the applier fails loud). **Refreshed at the b10679 bump:** upstream rewrote `tests/test-save-load-state.cpp`'s `main()` to take a `--models DIR` option, which it strips itself into a `filtered_argv` before calling `common_params_parse(fargc, filtered_argv.data(), …)`. That call site therefore stopped qualifying for the `_main()` flip — by this patch's own rule a caller that builds its own argv must use `common_params_parse` directly, so its argv is kept — and the hunk was **dropped** rather than refreshed (37 → 36 files). Caveat for whoever submits this upstream: that `main()` now filters a possibly-mojibake Windows argv *before* any UTF-8 recovery, so the fully correct upstream form there is recover-then-filter, not a one-line flip. It is out of scope for the downstream carry because `LLAMA_BUILD_TESTS` is OFF here, so the file is never compiled. **Still required at b10679, verified rather than assumed:** `common_params_parse` in pristine `b10679:common/arg.cpp` still carries the `#ifdef _WIN32` count-guarded `argv = utf8.ptrs.data()` override, and `common_params_parse_main` appears nowhere in `b10679:common/arg.h` — upstream has not adopted the fix. The upstream-facing write-up, including a standalone reproducer that makes llama.cpp's own `test-arg-parser` fail on unmodified `master`, lives in [docs/upstream-investigation-win32-argv-substitution.md](docs/upstream-investigation-win32-argv-substitution.md). **Reported upstream as [ggml-org/llama.cpp#26416](https://github.com/ggml-org/llama.cpp/issues/26416)** (2026-08-01, label `bug-unconfirmed`, first bad commit `508a475`); the issue asks which of the two directions the maintainers prefer before a PR is opened, so this patch stays downstream until they answer. |
+| `0001-win32-arg-parse-embed-guard.patch` | Windows JNI regression from llama.cpp **#24779** (introduced b9739): on Windows `common_params_parse` re-derived argv from the **process** command line (`GetCommandLineW`) and adopted it, so an embedded/JNI caller (`java.exe`) lost its `--model …` args → "Failed to parse model parameters". b9789 narrowed the unconditional override to a **count-guard** (`if (static_cast<int>(utf8.buf.size()) == argc) { argv = utf8.ptrs.data(); }`), but that is exactly the variant the project already found breaks its Windows server-integration tests (when the embedded argv length coincides with `java.exe`'s). The patch carries the **complete upstream change** (so it can be submitted to llama.cpp verbatim and then dropped here): **(1)** `common_params_parse` parses **exactly the argv it is given** (no `GetCommandLineW` magic) and a new `common_params_parse_main()` wrapper holds the UTF-8 recovery for the standalone tools' `main()` (`common/arg.{cpp,h}`); **(2)** the **~34 standalone `main()` call sites** (every `common_params_parse(argc, argv, …)` across `tools/*`, `examples/*` and the `tests/*` programs) flip to `common_params_parse_main()`; **(3)** a `tests/test-arg-parser.cpp` regression case pins that `common_params_parse` honors a caller-supplied argv. The embedded caller (`jllama.cpp`) keeps calling `common_params_parse` and is never overridden. **Our subproject build compiles only the `arg.{cpp,h}` core** — `LLAMA_BUILD_TOOLS`/`LLAMA_BUILD_TESTS` are OFF for a FetchContent subproject — so the flips + test are applied-but-not-compiled here; they were validated via a one-off `-DLLAMA_BUILD_TOOLS=ON -DLLAMA_BUILD_TESTS=ON` build (the new test compiles and its asserts pass; `test-arg-parser`'s only red there is the live `ggml.ai` download check, which is sandbox-network, not the patch). Because it spans **35 files** it must be refreshed on every llama.cpp bump (the applier fails loud). **Refreshed at the b10679 bump:** upstream rewrote `tests/test-save-load-state.cpp`'s `main()` to take a `--models DIR` option, which it strips itself into a `filtered_argv` before calling `common_params_parse(fargc, filtered_argv.data(), …)`. That call site therefore stopped qualifying for the `_main()` flip — by this patch's own rule a caller that builds its own argv must use `common_params_parse` directly, so its argv is kept — and the hunk was **dropped** rather than refreshed (37 → 36 files). Caveat for whoever submits this upstream: that `main()` now filters a possibly-mojibake Windows argv *before* any UTF-8 recovery, so the fully correct upstream form there is recover-then-filter, not a one-line flip. It is out of scope for the downstream carry because `LLAMA_BUILD_TESTS` is OFF here, so the file is never compiled. **Refreshed the same way at the b11236 bump:** upstream #29426 rewrote `tests/test-recurrent-state-rollback.cpp`'s `main()` into the identical `--models DIR` / `filtered_argv` shape, so that hunk was dropped too (36 → 35 files); the same recover-then-filter caveat applies to it. **Still required at b10679, verified rather than assumed:** `common_params_parse` in pristine `b10679:common/arg.cpp` still carries the `#ifdef _WIN32` count-guarded `argv = utf8.ptrs.data()` override, and `common_params_parse_main` appears nowhere in `b10679:common/arg.h` — upstream has not adopted the fix. The upstream-facing write-up, including a standalone reproducer that makes llama.cpp's own `test-arg-parser` fail on unmodified `master`, lives in [docs/upstream-investigation-win32-argv-substitution.md](docs/upstream-investigation-win32-argv-substitution.md). **Reported upstream as [ggml-org/llama.cpp#26416](https://github.com/ggml-org/llama.cpp/issues/26416)** (2026-08-01, label `bug-unconfirmed`, first bad commit `508a475`); the issue asks which of the two directions the maintainers prefer before a PR is opened, so this patch stays downstream until they answer. |
 | `0002-server-preserve-caller-load-progress-callback.patch` | Load-progress-callback regression introduced in llama.cpp **b9789**: `server_context::load_model` (`tools/server/server-context.cpp`) now **unconditionally** installs the server's own load-progress reporter on `params_base.load_progress_callback` immediately before `common_init_from_params`, clobbering any callback the embedding caller already set. libjllama's `LoadProgressCallback` feature wires `common_params.load_progress_callback` to a JNI trampoline *before* calling `load_model`, so the bump silently killed it — `LoadProgressCallbackTest` saw zero progress updates and the abort-on-`false` path never threw. The patch guards the assignment with `if (params_base.load_progress_callback == nullptr)`, so the server installs its own reporter **only when the caller hasn't** — a caller-supplied callback survives and fires during load. Standalone `llama-server` (no caller callback, so the field is null) is unaffected. Same JNI-vs-standalone divergence class as `0001`. **The guard is `== nullptr || == load_progress_callback`, and the second disjunct must never be dropped:** `load_progress_text` is a **local** of `load_model()`, and upstream re-assigns both fields on every call so the `user_data` always points at the current frame. `load_model()` runs a **second** time when resuming from the sleeping state (`--sleep-idle-seconds`), and by then `params_base` holds *our own* callback from the first load — a bare nullptr check skips the re-assignment and leaves `user_data` pointing into a **dead stack frame**, which segfaults inside `load_progress_callback()` on the first request after an idle window. That was a latent defect in this patch from the day it was written; only a second `load_model()` can reach it, and nothing exercised sleep until `IdleSleepWakeIntegrationTest` was added. |
 | `0003-pr22393-server-add-slot-prompt-similarity-getter-setter.patch` | **Upstream-PR carry** of [ggml-org/llama.cpp#22393](https://github.com/ggml-org/llama.cpp/pull/22393) ("server : add slot_prompt_similarity getter/setter"). Purely additive: adds `server_context::get_slot_prompt_similarity()` / `set_slot_prompt_similarity(float)` (`tools/server/server-context.{cpp,h}`) so an embedding/JNI caller can query and tune the slot-selection threshold at runtime without reloading the model. Verbatim copy of the PR, which **upstream closed without merging** (rejected as exposing unsafe internal state — see the patch header). Carried permanently; it will not be droppable via a version bump. |
 | `0007-server-attach-http-frontend.patch` | **Adds `llama_server_attach(argc, argv, server_context&)`** so the `NativeServer` *attach mode* can serve an **already-loaded `LlamaModel`** over the upstream HTTP frontend — no second model load, no `start_loop()`; the LlamaModel's worker keeps driving the shared `server_context` and the HTTP routes post tasks to its queue (the queue is the synchronization point). Mechanically: (1) extracts the **pure core route table** (`health` … `slots`) out of `llama_server()` into `static void llama_server_register_common_routes(ctx_http, routes)` (shared, so the two entry points cannot drift on the core endpoint set). **Scope note (narrowed at the b10154 bump):** the helper deliberately carries **only** the stable, state-independent route table — **not** the resumable-streaming routes (their handlers differ between router / non-router), the GCP-compat shim, or the experimental **CORS-proxy / MCP-server / built-in-tools** wiring. b10154 (upstream MCP-server support) moved the streaming routes into the middle of that block and coupled tools/CORS to a per-call `server_mcp mcp_mgr` lifecycle, so the earlier contiguous "route-table + CORS-proxy + tools" extraction is no longer possible; `llama_server()` keeps all of that inline, **byte-identical to upstream b10154** (only the route-table block is factored out). (2) adds `llama_server_attach`, which parses only the HTTP-side argv via `common_params_parse`, starts the stream-session GC + `server_http_context`, registers the common route table, the **non-router** resumable-streaming handlers (upstream b10154 paths `/v1/stream` GET/DEL + `/v1/streams/lookup` POST), the GCP-compat shim, and **403 "disabled" stubs for `/cors-proxy` + `/tools`** (attach mode does not wire the experimental CORS-proxy / MCP / built-in-tools host — those belong to a full `llama-server`, not an embedded model), marks ready immediately (model already loaded), and blocks on the HTTP thread until `llama_server_request_shutdown()` — never calling `common_init()`, backend init, `ctx_server.terminate()` or `llama_backend_free()` (the embedding caller owns those). Applies after `0001`+`0006` (same file); closes the "NativeServer — reuse an already-loaded LlamaModel" TODO. Upstream-submittable ("server: let embedding callers attach the HTTP frontend to an existing server_context"). **Refreshed at the b10519 bump:** upstream #26347 dropped the API key from the `/models` + `/v1/models` public-endpoint set and deleted the two trailing `// public endpoint (no API key check)` comments on those route registrations. Those two lines sit inside this patch's route-table removal block, so `git apply` failed ("patch does not apply", `server.cpp:258`) at **every** tag from b10519 on; the fix was to drop the now-wrong comment from all four affected lines (2 on the `-` side, 2 in the extracted helper on the `+` side), keeping the helper byte-identical to the block it replaces. **This is the invariant to re-check on every bump:** the `+` side of `llama_server_register_common_routes()` must stay a verbatim copy of the route table it factors out of `llama_server()`. **Refreshed at the b11104 bump** (upstream #28690, multi-address `--host`): `server_http_context` lost its single `thread` and `listening_address` members in favour of `join()` and a `listening_addresses` vector, one listener thread per bound address. The patch still *applied* cleanly there — only its own `+` lines named the removed members — so the applier could not see it; `llama_server_attach` now logs every address and blocks in `ctx_http.join()`, exactly as upstream's `llama_server()` does. |
@@ -1795,7 +1795,7 @@ 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 b11222`.
+llama.cpp is fetched via CMake FetchContent, pinned to `GIT_TAG b11236`.
 
 **GoogleTest** is a separate `BUILD_TESTING`-only FetchContent (`GIT_TAG v1.18.0`), used solely
 by the `jllama_test` C++ unit-test binary — not by the shipped library, and not coupled to the

@@ -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 b11222](https://img.shields.io/badge/llama.cpp-%23b11222-informational)](https://github.com/ggml-org/llama.cpp/releases/tag/b11222)  
+[![llama.cpp b11236](https://img.shields.io/badge/llama.cpp-%23b11236-informational)](https://github.com/ggml-org/llama.cpp/releases/tag/b11236)  
 [![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)