Merge remote-tracking branch 'ggerganov/master'

* ggerganov/master: (335 commits)
  server : add Voice Activity Detection (VAD) support (ggml-org#3246)
  cli : fix short name conflict for vad options [no ci] (ggml-org#3247)
  ruby : add .gitignore entries for ext directory (ggml-org#3245)
  ci : update windows runner to windows-2022 (ggml-org#3242)
  ruby : add cleaning of library names in dependencies (ggml-org#3241)
  ggml : fix weak alias win32 (#0)
  android : fix builds (#0)
  sync : ggml
  files : remove old sources (part 2)
  sync : ggml
  files : remove old sources
  talk-llama : sync llama.cpp
  sync : ggml
  metal : use less stack memory in FA kernel (llama/14088)
  ggml-cpu : split arch-specific implementations (llama/13892)
  cuda : fix device sync on buffer clear (llama/14033)
  CANN: Simplify the environment variable setting(#13104)
  sycl: Add reorder to Q6_K mmvq implementation (llama/13885)
  cuda : fix buffer type check with integrated GPUs (llama/14069)
  SYCL: Implement few same quantized type copy kernels (llama/13739)
  ...

Author: bygreencn

.devops/main-cuda.Dockerfile

@@ -13,8 +13,6 @@ WORKDIR /app
 ARG CUDA_DOCKER_ARCH=all
 # Set nvcc architecture
 ENV CUDA_DOCKER_ARCH=${CUDA_DOCKER_ARCH}
-# Enable cuBLAS
-ENV GGML_CUDA=1
 
 RUN apt-get update && \
     apt-get install -y build-essential libsdl2-dev wget cmake git \
@@ -25,7 +23,8 @@ ENV CUDA_MAIN_VERSION=12.3
 ENV LD_LIBRARY_PATH /usr/local/cuda-${CUDA_MAIN_VERSION}/compat:$LD_LIBRARY_PATH
 
 COPY .. .
-RUN make base.en
+# Enable cuBLAS
+RUN make base.en CMAKE_ARGS="-DGGML_CUDA=1"
 
 FROM ${BASE_CUDA_RUN_CONTAINER} AS runtime
 ENV CUDA_MAIN_VERSION=12.3
@@ -37,4 +36,5 @@ RUN apt-get update && \
   && rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*
 
 COPY --from=build /app /app
+ENV PATH=/app/build/bin:$PATH
 ENTRYPOINT [ "bash", "-c" ]

.devops/main-intel.Dockerfile

@@ -0,0 +1,28 @@
+ARG ONEAPI_VERSION=2025.1.1-0-devel-ubuntu24.04
+
+FROM intel/oneapi-basekit:$ONEAPI_VERSION AS build
+WORKDIR /app
+
+RUN apt-get update && \
+    apt-get install -y build-essential libsdl2-dev wget cmake git \
+    && rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*
+
+COPY .. .
+# Enable SYCL
+ARG GGML_SYCL_F16=OFF
+RUN if [ "${GGML_SYCL_F16}" = "ON" ]; then \
+        echo "GGML_SYCL_F16 is set" \
+        && export OPT_SYCL_F16="-DGGML_SYCL_F16=ON"; \
+    fi && \
+    make base.en CMAKE_ARGS="-DGGML_SYCL=1 -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx ${OPT_SYCL_F16}"
+
+FROM intel/oneapi-basekit:$ONEAPI_VERSION AS runtime
+WORKDIR /app
+
+RUN apt-get update && \
+  apt-get install -y curl ffmpeg libsdl2-dev wget cmake git \
+  && rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*
+
+COPY --from=build /app /app
+ENV PATH=/app/build/bin:$PATH
+ENTRYPOINT [ "bash", "-c" ]

.devops/main-musa.Dockerfile

@@ -0,0 +1,29 @@
+ARG UBUNTU_VERSION=22.04
+# This needs to generally match the container host's environment.
+ARG MUSA_VERSION=rc4.0.1
+# Target the MUSA build image
+ARG BASE_MUSA_DEV_CONTAINER=mthreads/musa:${MUSA_VERSION}-mudnn-devel-ubuntu${UBUNTU_VERSION}
+# Target the MUSA runtime image
+ARG BASE_MUSA_RUN_CONTAINER=mthreads/musa:${MUSA_VERSION}-mudnn-runtime-ubuntu${UBUNTU_VERSION}
+
+FROM ${BASE_MUSA_DEV_CONTAINER} AS build
+WORKDIR /app
+
+RUN apt-get update && \
+    apt-get install -y build-essential libsdl2-dev wget cmake git \
+    && rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*
+
+COPY .. .
+# Enable muBLAS
+RUN make base.en CMAKE_ARGS="-DGGML_MUSA=1"
+
+FROM ${BASE_MUSA_RUN_CONTAINER} AS runtime
+WORKDIR /app
+
+RUN apt-get update && \
+  apt-get install -y curl ffmpeg wget cmake git \
+  && rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*
+
+COPY --from=build /app /app
+ENV PATH=/app/build/bin:$PATH
+ENTRYPOINT [ "bash", "-c" ]

.devops/main.Dockerfile

@@ -16,4 +16,5 @@ RUN apt-get update && \
   && rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*
 
 COPY --from=build /app /app
+ENV PATH=/app/build/bin:$PATH
 ENTRYPOINT [ "bash", "-c" ]

.dockerignore

@@ -0,0 +1,3 @@
+build*/
+.github/
+.devops/