Skip to content

Upgrade llama.cpp from b9151 to b9172 #143

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
bernardladenthin merged 1 commit into from
May 15, 2026
Merged

Upgrade llama.cpp from b9151 to b9172 #143

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 7 additions & 1 deletion CLAUDE.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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: **b9151**
Current llama.cpp pinned version: **b9172**

## Upgrading CUDA Version

Expand Down Expand Up @@ -275,6 +275,12 @@ Also review the project `CMakeLists.txt` for build-system-level breaks (e.g. ren
| ~b9150–b9151 | `tools/server/server-common.h` | New `SLT_TRC` and `SRV_TRC` macros (emit at `LOG_TRC` level); additive, no project changes required |
| ~b9150–b9151 | `tools/server/server-context.cpp` | New `server_slot::t_print_last` field + `print_timings_tg()` / `print_timings_pp()` methods: emit periodic in-flight token-generation and prompt-processing throughput to `SLT_INF` (throttled to ≥100 decoded tokens and ≥3 s interval); `server_context_impl` constructor now calls `mtmd_helper_log_set` unconditionally (was guarded by `!is_resume`); many `SLT_INF`/`SRV_WRN` downgraded to `SLT_TRC`/`SRV_INF`; compiled from upstream, no project JNI changes required |
| ~b9150–b9151 | `tools/server/server-task.cpp` | Several `SRV_WRN` calls downgraded to `SRV_INF`; one `SRV_WRN` upgraded to `SRV_ERR` for failed state restore; compiled from upstream, no project changes required |
| ~b9151–b9172 | `tools/mtmd/clip.h` | `clip_has_whisper_encoder()` removed from public API; not referenced by project — no changes required |
| ~b9151–b9172 | `tools/server/CMakeLists.txt` + `scripts/webui-download.cmake` (new) | WebUI assets no longer committed (`tools/server/public/` gitignored); provisioned at build time via HF bucket (`LLAMA_USE_PREBUILT_WEBUI=ON` default) or built from source (`LLAMA_BUILD_WEBUI`); project sets `LLAMA_BUILD_WEBUI=OFF CACHE BOOL "" FORCE` before FetchContent to skip asset download |
| ~b9151–b9172 | `common/common.h` | `common_params::webui` default made conditional on `LLAMA_WEBUI_DEFAULT_ENABLED` macro (falls back to `true` when undefined); compiled server sources unaffected |
| ~b9151–b9172 | `common/reasoning-budget.cpp` | `common_reasoning_budget_clone` rewritten to use `llama_sampler_init` properly; pure bug fix, no API change, no project changes required |
| ~b9151–b9172 | `ggml/src/ggml-cuda/fattn-mma-f16.cuh` + `mma.cuh` | AMD RDNA3 WMMA flash attention support; new `DATA_LAYOUT_I_MAJOR_SCRAMBLED`, `tile<16,16,half2,I_MAJOR_SCRAMBLED>`, extended config tables; internal CUDA backend, no project changes required |
| ~b9151–b9172 | `tools/server/server-chat.cpp` | Non-function Responses API tools now silently skipped (`continue`) instead of throwing; server behavior fix, no Java API change required |

## Build Commands

Expand Down
3 changes: 2 additions & 1 deletion CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,10 +104,11 @@ endif()
set(GGML_FMA ON CACHE BOOL "" FORCE)
set(GGML_F16C ON CACHE BOOL "" FORCE)
set(GGML_AVX512 OFF CACHE BOOL "" FORCE)
set(LLAMA_BUILD_WEBUI OFF CACHE BOOL "" FORCE)
Copy link
Copy Markdown

@claude claude Bot May 15, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Consider whether LLAMA_USE_PREBUILT_WEBUI also needs to be disabled. According to CLAUDE.md, upstream defaults to LLAMA_USE_PREBUILT_WEBUI=ON which downloads prebuilt WebUI assets. Setting LLAMA_BUILD_WEBUI=OFF prevents building from source, but the prebuilt download might still occur. If the goal is to fully avoid network I/O, you may also need:

set(LLAMA_USE_PREBUILT_WEBUI OFF CACHE BOOL "" FORCE)

Or confirm that LLAMA_BUILD_WEBUI=OFF alone is sufficient to prevent all WebUI asset provisioning.

FetchContent_Declare(
llama.cpp
GIT_REPOSITORY https://github.com/ggerganov/llama.cpp.git
GIT_TAG b9151
GIT_TAG b9172
)
FetchContent_MakeAvailable(llama.cpp)

Expand Down
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
![Java 8+](https://img.shields.io/badge/Java-8%2B-informational)
[![llama.cpp b9151](https://img.shields.io/badge/llama.cpp-%23b9151-informational)](https://github.com/ggml-org/llama.cpp/releases/tag/b9151)
[![llama.cpp b9172](https://img.shields.io/badge/llama.cpp-%23b9172-informational)](https://github.com/ggml-org/llama.cpp/releases/tag/b9172)
[![Maven Central](https://img.shields.io/maven-central/v/net.ladenthin/llama)](https://central.sonatype.com/artifact/net.ladenthin/llama)
[![Snapshot](https://img.shields.io/badge/snapshot-latest-informational)](https://central.sonatype.com/repository/maven-snapshots/net/ladenthin/llama/)

Expand Down
Loading