chore: bump llama.cpp to b10255

[leehack]

llama.cpp update

• Previous pin: b10236
• New pin: b10255
• Upstream release: https://github.com/ggml-org/llama.cpp/releases/tag/b10255
• Compare: ggml-org/llama.cpp@b10236...b10255

Upstream changelog

Release notes for b10255

Details

Extended SYCL oneDNN SDPA to non-FP16 KV caches (Q4_0–Q8_0 and FP32) (#25874)

• sycl: extend oneDNN SDPA to Q4_0-Q8_0 and F32 KV caches

Extends the oneDNN SDPA path (PR #25222) to handle non-F16 KV caches by
dequantizing or converting K/V to dense FP16 on-device before feeding
them into the SDPA graph. The fused systolic kernel then runs identically
to the native FP16 path.

Supported KV types:

• Q4_0, Q4_1, Q5_0, Q5_1, Q8_0: to_fp16_sycl / to_fp16_nc_sycl
• F32: cont_to_f16_sycl
• BF16 and IQ types are excluded (no conversion kernel available)

Gate: non-F16 requires K >= 1024 and Q >= 32 (prefill only).
F16 KV runs at any length (existing behavior).

Also includes the stream sync fix (stream->wait_and_throw() unconditional,
PR #25741 by @malsbat) and removal of V_is_K_view aliasing (K and V are
always dequantized to separate buffers).

Co-Authored-By: Claude noreply@anthropic.com

• docs: drop GGML_SYCL_FA_DEBUG from SYCL.md (not shipped in this PR)
  Co-Authored-By: Claude noreply@anthropic.com

---

Co-authored-by: Claude noreply@anthropic.com

Website:

• https://llama.app

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)
• Ubuntu x64 (SYCL FP16)

Android:

• Android arm64 (CPU)

Windows:

• Windows x64 (CPU)
• Windows arm64 (CPU)
• Windows arm64 (OpenCL Adreno)
• Windows x64 (CUDA 12) - CUDA 12.4 DLLs
• Windows x64 (CUDA 13) - CUDA 13.3 DLLs
• Windows x64 (Vulkan)
• Windows x64 (OpenVINO)
• Windows x64 (SYCL)
• 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 b10236 to b10255 (first 80)

• llama : MTP support for DeepSeek V3.2 (#26457) (2b63e06)
• model: MTP support for Qwen3-Next (#25589) (4ed2b13)
• server: (tools) add x-tool-cwd header (#26420) (f2b52a8)
• server: add notice for upcoming default port change 8080 --> 9931 (#26508) (0b14b87)
• CUDA: Fix data-races when reusing SMEM in block_reduce (#26385) (9bd4c09)
• CUDA: Add backend sampler for penalties sampler (#25262) (96278e3)
• llama : allocate indexer cache only in "full" indexer layers (#26474) (563dec8)
• model: M3: Move MSA into a new memory implementation (#26338) (67d5978)
• graph : fix unused input tensors in minimax m3 graph (#26519) (c50b34a)
• opencl: route large q6_K lm_head to the flat GEMV (#26427) (39eab74)
• ggml: use dynamic allocation for split graph inputs (#22789) (dbadb68)
• vocab : validate default special token ids (#26506) (e8e06f7)
• server: add get_info tool (#26522) (99111b1)
• tests: add model resolution test on synthetic repo listings (#26172) (ee0445c)
• model : support MTP in GLM-4.7-Flash (#24868) (57c0921)
• vendor : update BoringSSL to 0.20260803.0 (#26523) (fe2adf0)
• vendor : update cpp-httplib to 0.52.0 (#26485) (94bc47f)
• chat : add new template for DeepSeek V4 Flash 0731 (#26398) (0ef6e55)
• Extended SYCL oneDNN SDPA to non-FP16 KV caches (Q4_0–Q8_0 and FP32) (#25874) (66fa168)

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.

[Copilot]

Pull request overview

Updates the pinned llama.cpp release tag used by llama-web-bridge builds/CI to the next upstream version, so the bridge compiles and ships against the newer llama.cpp codebase.

Changes:

• Bump the pinned llama.cpp tag from b10236 to b10255.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.