chore: bump llama.cpp to b9557

[github-actions]

llama.cpp update

• Previous pin: b9165
• New pin: b9557
• Upstream release: https://github.com/ggml-org/llama.cpp/releases/tag/b9557
• Compare: ggml-org/llama.cpp@b9165...b9557

Upstream changelog

Release notes for b9557

Details

cuda: reset cuda context after reading memory size (#23935)

• cuda: reset device in get_memory function if no backend is active

• also count device and host buffers

• exclude hip and musa from counting and device reset

• use device mutex instead of atomic

• undo backend_free function move

macOS/iOS:

• macOS Apple Silicon (arm64)
• macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
• macOS Intel (x64)
• iOS XCFramework

Linux:

• Ubuntu x64 (CPU)
• Ubuntu arm64 (CPU)
• Ubuntu s390x (CPU)
• Ubuntu x64 (Vulkan)
• Ubuntu arm64 (Vulkan)
• Ubuntu x64 (ROCm 7.2)
• Ubuntu x64 (OpenVINO)
• Ubuntu x64 (SYCL FP32) DISABLED

Android:

• Android arm64 (CPU)

Windows:

• Windows x64 (CPU)
• Windows arm64 (CPU)
• Windows x64 (CUDA 12) - CUDA 12.4 DLLs
• Windows x64 (CUDA 13) - CUDA 13.3 DLLs
• Windows x64 (Vulkan)
• Windows x64 (SYCL) DISABLED
• Windows x64 (HIP)

openEuler:

• DISABLED
• openEuler x86 (310p)
• openEuler x86 (910b, ACL Graph)
• openEuler aarch64 (310p)
• openEuler aarch64 (910b, ACL Graph)

UI:

• UI

Commit range

Commits from b9165 to b9557 (first 80)

• ci : move most slim jobs to self-hosted runners (#23619) (28123a3)
• perplexity : fix even more integer overflows (#23623) (6d57c26)
• server: fix checkpoints creation (#22929) (e2ef8fe)
• vendor : update cpp-httplib to 0.45.1 (#23639) (9627d0f)
• ui: media attachments before text (#23467) (b964876)
• ggml : Parallelize quant LUT init (#23595) (826539c)
• ci : install host compiler on android-ndk build (#23630) (d55fb97)
• llama : document that only one on-device state can be saved per sequence (#23520) (314e729)
• ci : fix pre-tokenizer-hashes check (#23651) (062d311)
• ci : update spacemit toolchain url and enhance curl command (#23642) (5fdf07e)
• server: MTP layer kv-cache should respect draft type ctk (#23646) (6c4cbdc)
• ggml: gguf_init_from_callback and gguf_init_from_buffer (#22341) (66efd13)
• TP: fix ggml context size calculation (#22616) (ae251b5)
• ggml-alloc: fix out-of-bounds read in ggml_dyn_tallocr_remove_block (ggml/1492) (fa97041)
• ggml.h: correct ggml_silu_back arg docstring (a=dy, b=x) (ggml/1500) (b251f74)
• ggml : bump version to 0.12.1 (ggml/1508) (ce5890b)
• sync : ggml (22307b3)
• ggml : bump version to 0.13.0 (ggml/1510) (45158f4)
• sync : ggml (d161ea7)
• convert : add compressed-tensors NVFP4 support (#21095) (a4d2d4a)
• ui: fix stop/continue during an agentic loop (#23356) (5a4126a)
• CUDA: add fast walsh-hadamard transform (#23615) (c1f1e28)
• model: tag ffn_latent as MUL_MAT to fix buft probe (#23664) (328874d)
• ci : reduce PR jobs by matching backend paths (#23675) (302e2c2)
• snapdragon: bump toolchain docker to v0.7 to fix ui build issues (#23680) (4bead4e)
• metal : add apple device id (#23566) (35c9b1f)
• CUDA: missing PDL sync for FWHT, better fallback (#23690) (192d8ae)
• [WebGPU] Check batch_compute_passes before sending passes when not doing GPU profiling (#23457) (54121f7)
• ggml-webgpu: Add MMVQ path for Q4/Q8/Q2_K/Q4_K and clean up legacy MUL_MAT pipeline (#23594) (1506d39)
• model : add support for talkie-1930-13b (#22596) (c9d9829)
• tests: test-backend-ops -j to run tests in parallel (#23637) (7623de1)
• SYCL: implement ggml_sycl_pool_vmm (#22862) (581d020)
• models : Attach Mistral3 NVFP4 weight scales (#23629) (6fe90de)
• convert : support Gemma4ForCausalLM architecture (#23682) (dbe9c0c)
• ci : reduce (disable SYCL and CANN builds/releases) (#23705) (3dc7684)
• ci : move sanitizer jobs to self-hosted runners (#23713) (ef41a69)
• ci : move more CPU jobs to self-hosted runners (#23715) (678d43d)
• hexagon: add support for CONCAT op (#23648) (ef66bfa)
• ci : remove vulkan SDK dep from webgpu job (#23718) (3a3ed15)
• vulkan: optimize conv2d and implement coopmat1 support (#22620) (7799d31)
• ci : move macos jobs to the apple workflow + fix names (#23721) (5190c2e)
• ci : add [no release] keyword + fix sanitizer builds (#23728) (35a74c8)
• ci : move [no release] check to dedicated check_release job (#23734) (08bc21b)
• ci : do not allocate ccache for 3rd-party hosted runners (#23730) (0d18aaa)
• ggml-zendnn : fixed naming of matmul function (#20964) (b4c0549)
• server : fix the log message when using SSL (#23393) (7085492)
• convert: add MiniCPM5 tokenizer support (#23384) (9777256)
• docs : fix duplicated "the" in granitevision and model-conversion docs (#23767) (1d971bb)
• ci : add ccache to server builds + fix undefined sanitizer build (#23763) (0d227ec)
• vulkan: avoid preferring transfer queue on AMD UMA devices (#22455) (4d8cc0c)
• ci : remove wasm test (#23733) (b3a739c)
• ci : fix windows ccaches (#23777) (9f0e4b1)
• common : fix env names to all have LLAMA_ARG_ prefix (#23778) (6b4e4bd)
• ci : bump cuda release to 13.3 (#23749) (2d0656f)
• CUDA: restrict PDL to CTK >= 12.3 due to MSVC issues (#23742) (fda8528)
• pyproject : add conversion folder and update dependencies (#23746) (87b0a60)
• vendor : update cpp-httplib to 0.46.0 (#23650) (617255d)
• ci : move ARM jobs to self-hosted + disable kleidiai mac release (#23780) (ba4dd0b)
• vulkan: add REPEAT op support for f16 to f16. (#23298) (837bb6b)
• vulkan: use GL_NV_cooperative_matrix_decode_vector for faster matmul (#23541) (b36eefc)
• vulkan: Switch MUL_MAT_VEC to 4 K per iteration for F16/32 (#22887) (c6e4088)
• ggml-webgpu: Fix how to dispatch WG to some ops (#23750) (c40006a)
• hexagon: add support for Q4_1 in MUL_MAT and MUL_MAT_ID (#23647) (aa50b2c)
• ggml-webgpu: remove legacy constants (#23672) (f12cc6d)
• opencl: OP_GATED_DELTA_NET (#23312) (8ad8aef)
• Hexagon: OP_GATED_DELTA_NET K>1 support (#23531) (939a7dd)
• ci : refactor (#23789) (491c4d7)
• ggml: fixed Arm SVE usage bug in vec.h, vec.cpp (#22841) (e31cdaa)
• convert : add FP8 to Q8 conversion (#23250) (c522908)
• perplexity : fix format specifier in LOG_ERR (#23788) (48e7eae)
• cuda : fix KQ mask offset integer overflow in fattn MMA kernel (#23610) (09e7b76)
• docker : add ZenDNN Dockerfile (#23716) (e8d2567)
• server, ui : Add support for HTTP ETags in llama-server (#23701) (d205df6)
• vulkan: Fix memory logger unsafe iterator access (#23667) (91eb8f4)
• vulkan: fix wrong index variable in inner loop (#23665) (7c48fb8)
• chat : add Granite 4.1 chat template (#23518) (bb771cb)
• vulkan: fast path for walsh-hadamard transform (#23687) (48e7078)
• hexagon: minor refresh for HMX FA and MM (#23796) (a919001)
• server: minor tweaks to use more cpp features (#23785) (0b24686)
• CUDA: route batch>=4 quantized matmul to MMQ on AMD MFMA hardware (#23227) (bc81d47)

Web bridge review focus

Please pay extra attention to upstream changes touching:

• WebGPU, WASM, Emscripten, pthreads, or memory64 build behavior
• ggml backend APIs used by the bridge
• model loading, tokenizer, chat template, context/state persistence, or cache semantics
• CMake/build flags that can affect the generated JS/WASM artifacts

Validation

• Emscripten build passed
• Browser WebGPU/state-persistence smoke passed
• Generated bridge artifacts include wasm32 and memory64 outputs
• No stale hard-coded llama.cpp tag remains in CI/publish defaults

Automation behavior

This PR is managed from the stable branch automation/bump-llama-cpp. If another llama.cpp release appears before merge, the scheduled workflow updates this same PR instead of opening a duplicate. The workflow skips if a non-automation PR already changes llama_cpp.version.