chore(deps): bump the pip group across 4 directories with 1 update

Bumps the pip group with 1 update in the /backend/python/ace-step directory: torch.
Bumps the pip group with 1 update in the /backend/python/llama-cpp-quantization directory: torch.
Bumps the pip group with 1 update in the /backend/python/sglang directory: torch.
Bumps the pip group with 1 update in the /backend/python/vllm-omni directory: torch.


Updates `torch` from 2.10.0+rocm7.0 to 2.12.0+cpu

Updates `torch` from 2.10.0+rocm7.0 to 2.12.0+cpu

Updates `torch` from 2.10.0+rocm7.0 to 2.12.0+cpu

Updates `torch` from 2.10.0+rocm7.0 to 2.12.0+cpu

Updates `torch` from 2.10.0 to 2.12.0+cpu

Updates `torch` from 2.10.0 to 2.12.0+cpu

Updates `torch` from 2.10.0 to 2.12.0+cpu

Updates `torch` from 2.10.0 to 2.12.0+cpu

Updates `torch` from 2.9.0 to 2.12.0+cpu

Updates `torch` from 2.9.0 to 2.12.0+cpu

Updates `torch` from 2.9.0 to 2.12.0+cpu

Updates `torch` from 2.9.0 to 2.12.0+cpu

Updates `torch` from 2.7.0 to 2.12.0+cu130

Updates `torch` from 2.7.0 to 2.12.0+cu130

Updates `torch` from 2.7.0 to 2.12.0+cu130

Updates `torch` from 2.7.0 to 2.12.0+cu130

---
updated-dependencies:
- dependency-name: torch
  dependency-version: 2.12.0+cpu
  dependency-type: direct:production
- dependency-name: torch
  dependency-version: 2.12.0+cpu
  dependency-type: direct:production
- dependency-name: torch
  dependency-version: 2.12.0+cpu
  dependency-type: direct:production
- dependency-name: torch
  dependency-version: 2.12.0+cu130
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>

backend/python/ace-step/requirements-hipblas.txt

@@ -1,5 +1,5 @@
 --extra-index-url https://download.pytorch.org/whl/rocm7.0
-torch==2.10.0+rocm7.0
+torch==2.12.0+cpu
 torchaudio
 torchvision
 

backend/python/fish-speech/requirements.txt

@@ -7,3 +7,7 @@ setuptools
 six
 scipy
 numpy
+# fish-speech is installed editable with --no-build-isolation, so the build
+# backends of its transitive deps must already be in the venv. One of them
+# builds a Rust extension and needs setuptools-rust present at metadata time.
+setuptools-rust

backend/python/llama-cpp-quantization/install.sh

@@ -11,14 +11,31 @@ fi
 EXTRA_PIP_INSTALL_FLAGS+=" --upgrade "
 installRequirements
 
-# Fetch convert_hf_to_gguf.py from llama.cpp
+# Fetch convert_hf_to_gguf.py from llama.cpp.
+# Upstream split the model-specific logic out of the single file into a
+# sibling `conversion/` package (convert_hf_to_gguf.py now does
+# `from conversion import ...`), so a single-file download no longer runs —
+# it fails with `ModuleNotFoundError: No module named 'conversion'`. We clone
+# the repo and copy both the script and the package; Python puts the script's
+# own directory on sys.path[0], so the package resolves when placed beside it.
 LLAMA_CPP_CONVERT_VERSION="${LLAMA_CPP_CONVERT_VERSION:-master}"
+LLAMA_CPP_SRC="${EDIR}/llama.cpp"
 CONVERT_SCRIPT="${EDIR}/convert_hf_to_gguf.py"
-if [ ! -f "${CONVERT_SCRIPT}" ]; then
-    echo "Downloading convert_hf_to_gguf.py from llama.cpp (${LLAMA_CPP_CONVERT_VERSION})..."
-    curl -L --fail --retry 3 \
-        "https://raw.githubusercontent.com/ggml-org/llama.cpp/${LLAMA_CPP_CONVERT_VERSION}/convert_hf_to_gguf.py" \
-        -o "${CONVERT_SCRIPT}" || echo "Warning: Failed to download convert_hf_to_gguf.py."
+
+cloneLlamaCpp() {
+    if [ ! -d "${LLAMA_CPP_SRC}/.git" ]; then
+        git clone --depth 1 --branch "${LLAMA_CPP_CONVERT_VERSION}" \
+            https://github.com/ggml-org/llama.cpp.git "${LLAMA_CPP_SRC}" 2>/dev/null || \
+        git clone --depth 1 https://github.com/ggml-org/llama.cpp.git "${LLAMA_CPP_SRC}"
+    fi
+}
+
+if [ ! -f "${CONVERT_SCRIPT}" ] || [ ! -d "${EDIR}/conversion" ]; then
+    echo "Fetching convert_hf_to_gguf.py + conversion/ from llama.cpp (${LLAMA_CPP_CONVERT_VERSION})..."
+    cloneLlamaCpp
+    cp "${LLAMA_CPP_SRC}/convert_hf_to_gguf.py" "${CONVERT_SCRIPT}"
+    rm -rf "${EDIR}/conversion"
+    cp -r "${LLAMA_CPP_SRC}/conversion" "${EDIR}/conversion"
 fi
 
 # Install gguf package from the same llama.cpp commit to keep them in sync
@@ -41,12 +58,7 @@ QUANTIZE_BIN="${EDIR}/llama-quantize"
 if [ ! -x "${QUANTIZE_BIN}" ] && ! command -v llama-quantize &>/dev/null; then
     if command -v cmake &>/dev/null; then
         echo "Building llama-quantize from llama.cpp (${LLAMA_CPP_CONVERT_VERSION})..."
-        LLAMA_CPP_SRC="${EDIR}/llama.cpp"
-        if [ ! -d "${LLAMA_CPP_SRC}" ]; then
-            git clone --depth 1 --branch "${LLAMA_CPP_CONVERT_VERSION}" \
-                https://github.com/ggml-org/llama.cpp.git "${LLAMA_CPP_SRC}" 2>/dev/null || \
-            git clone --depth 1 https://github.com/ggml-org/llama.cpp.git "${LLAMA_CPP_SRC}"
-        fi
+        cloneLlamaCpp  # reuses the clone fetched for convert_hf_to_gguf.py
         cmake -B "${LLAMA_CPP_SRC}/build" -S "${LLAMA_CPP_SRC}" -DGGML_NATIVE=OFF -DBUILD_SHARED_LIBS=OFF
         cmake --build "${LLAMA_CPP_SRC}/build" --target llama-quantize -j"$(nproc 2>/dev/null || echo 2)"
         cp "${LLAMA_CPP_SRC}/build/bin/llama-quantize" "${QUANTIZE_BIN}"

backend/python/llama-cpp-quantization/requirements-cpu.txt

@@ -1,5 +1,5 @@
 --extra-index-url https://download.pytorch.org/whl/cpu
-torch==2.10.0
+torch==2.12.0+cpu
 transformers>=4.56.2
 huggingface-hub>=1.3.0
 sentencepiece

backend/python/llama-cpp-quantization/requirements-mps.txt

@@ -1,4 +1,4 @@
-torch==2.10.0
+torch==2.12.0+cpu
 transformers>=4.56.2
 huggingface-hub>=1.3.0
 sentencepiece

backend/python/sglang/install.sh

@@ -85,9 +85,15 @@ if [ "x${BUILD_TYPE}" == "x" ] || [ "x${FROM_SOURCE:-}" == "xtrue" ]; then
     # The resulting binary still requires an AVX-512 capable CPU at runtime,
     # same constraint sglang upstream documents in docker/xeon.Dockerfile.
 
+    # Pin the source build to the same release the GPU path floors on
+    # (0.5.11, see requirements-cublas12-after.txt). An unpinned master clone
+    # pulls in newer CPU kernels (e.g. mamba/fla.cpp) that fail to compile
+    # (constexpr non-constant + kineto_LIBRARY-NOTFOUND). Bump deliberately.
+    SGLANG_VERSION="${SGLANG_VERSION:-v0.5.11}"
     _sgl_src=$(mktemp -d)
     trap 'rm -rf "${_sgl_src}"' EXIT
-    git clone --depth 1 https://github.com/sgl-project/sglang "${_sgl_src}/sglang"
+    git clone --depth 1 --branch "${SGLANG_VERSION}" \
+        https://github.com/sgl-project/sglang "${_sgl_src}/sglang"
 
     # Patch -march=native → -march=sapphirerapids in the CPU kernel CMakeLists
     sed -i 's/-march=native/-march=sapphirerapids/g' \

backend/python/sglang/requirements-cpu.txt

@@ -1,6 +1,6 @@
 --extra-index-url https://download.pytorch.org/whl/cpu
 accelerate
-torch==2.9.0
+torch==2.12.0+cpu
 torchvision
 torchaudio
 transformers

backend/python/sglang/requirements-cublas12.txt

@@ -6,7 +6,7 @@
 # for cublas12 so uv consults this index alongside PyPI.
 --extra-index-url https://download.pytorch.org/whl/cu128
 accelerate
-torch==2.9.1
+torch==2.12.0+cpu
 torchvision
 torchaudio
 transformers

backend/python/vllm-omni/requirements-cublas12.txt

@@ -1,4 +1,4 @@
 accelerate
-torch==2.7.0
+torch==2.12.0+cu130
 transformers
 bitsandbytes

backend/rust/kokoros/src/service.rs

@@ -570,6 +570,43 @@ impl Backend for KokorosService {
     ) -> Result<Response<backend::Result>, Status> {
         Err(Status::unimplemented("Not supported"))
     }
+
+    async fn sound_detection(
+        &self,
+        _: Request<backend::SoundDetectionRequest>,
+    ) -> Result<Response<backend::SoundDetectionResponse>, Status> {
+        Err(Status::unimplemented("Not supported"))
+    }
+
+    async fn depth(
+        &self,
+        _: Request<backend::DepthRequest>,
+    ) -> Result<Response<backend::DepthResponse>, Status> {
+        Err(Status::unimplemented("Not supported"))
+    }
+
+    async fn token_classify(
+        &self,
+        _: Request<backend::TokenClassifyRequest>,
+    ) -> Result<Response<backend::TokenClassifyResponse>, Status> {
+        Err(Status::unimplemented("Not supported"))
+    }
+
+    async fn score(
+        &self,
+        _: Request<backend::ScoreRequest>,
+    ) -> Result<Response<backend::ScoreResponse>, Status> {
+        Err(Status::unimplemented("Not supported"))
+    }
+
+    type ForwardStream = ReceiverStream<Result<backend::ForwardReply, Status>>;
+
+    async fn forward(
+        &self,
+        _: Request<tonic::Streaming<backend::ForwardRequest>>,
+    ) -> Result<Response<Self::ForwardStream>, Status> {
+        Err(Status::unimplemented("Not supported"))
+    }
 }
 
 #[cfg(test)]

gallery/index.yaml

@@ -1,4 +1,52 @@
 ---
+- name: "qwen-agentworld-35b-a3b"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/unsloth/Qwen-AgentWorld-35B-A3B-GGUF
+  description: |
+    # Qwen-AgentWorld-35B-A3B
+
+    📑 Technical Report |
+    📖 Blog |
+    🤗 Hugging Face |
+    🤖 ModelScope |
+    💻 GitHub |
+    🖥️ Demo
+
+    > [!Note]
+    > This repository contains the model weights and configuration files for **Qwen-AgentWorld-35B-A3B**, a native language world model trained for agentic environment simulation.
+    >
+    > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, etc.
+
+    **Qwen-AgentWorld** is the first language world model to cover seven agent interaction domains within a single model. It simulates agentic environments via long chain-of-thought reasoning, predicting the next environment state given an agent's action and interaction history. Trained through a three-stage pipeline — CPT injects environment knowledge, SFT activates next-state-prediction reasoning, RL sharpens simulation fidelity — Qwen-AgentWorld is a **native world model**: environment modeling is the training objective from the CPT stage onward, not a post-hoc add-on.
+
+    ## Highlights
+
+    ...
+  license: "apache-2.0"
+  tags:
+    - llm
+    - gguf
+    - qwen
+  icon: https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/Qwen-AgentWorld/logo.png
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/Qwen-AgentWorld-35B-A3B-GGUF/Qwen-AgentWorld-35B-A3B-UD-Q4_K_M.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/Qwen-AgentWorld-35B-A3B-GGUF/Qwen-AgentWorld-35B-A3B-UD-Q4_K_M.gguf
+      sha256: e7a8eafdd8013443b6bcc4b6fb47b2d2025f772d359650b9ceb7d75971e22cad
+      uri: https://huggingface.co/unsloth/Qwen-AgentWorld-35B-A3B-GGUF/resolve/main/Qwen-AgentWorld-35B-A3B-UD-Q4_K_M.gguf
 - name: "ornith-1.0-9b"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls:

scripts/build/golang-darwin.sh

@@ -17,9 +17,15 @@ rm -rf "${BACKEND_DIR}"/build-*
 # run.sh's final `exec $CURDIR/<binary>` is the contract for what gets launched;
 # the binary is not always named after the backend (e.g. parakeet-cpp launches
 # parakeet-cpp-grpc), so derive it from run.sh and fall back to ${BACKEND}.
+#
+# Only scan the `exec` line(s): many run.sh select a runtime CPU variant via
+# unquoted `LIBRARY=$CURDIR/libgo<x>-avx512.so` lines, and a whole-file grep
+# would pick the last of those (avx512, which Darwin never builds) instead of
+# the binary — failing the check below for whisper/sam3-cpp/vibevoice-cpp/...
+# Also tolerate the exec being quoted (`exec "$CURDIR"/<binary>`).
 RUN_BINARY=""
 if [ -f "${BACKEND_DIR}/run.sh" ]; then
-        RUN_BINARY=$(grep -oE '\$CURDIR/[A-Za-z0-9._-]+' "${BACKEND_DIR}/run.sh" | grep -v 'ld\.so' | tail -1 | sed 's|\$CURDIR/||')
+        RUN_BINARY=$(grep -E '^[[:space:]]*exec[[:space:]]' "${BACKEND_DIR}/run.sh" | grep -oE '"?\$CURDIR"?/[A-Za-z0-9._-]+' | grep -v 'ld\.so' | tail -1 | sed -E 's|"?\$CURDIR"?/||')
 fi
 RUN_BINARY="${RUN_BINARY:-${BACKEND}}"