Merge remote-tracking branch 'bobqianic/fix-decoding' into fix_decoding

* bobqianic/fix-decoding: (436 commits)
  Add files via upload
  Update whisper.cpp
  whisper : optimize fft() function (ggerganov#2242)
  talk-llama : sync llama.cpp
  whisper : use ggml_backend_sched (ggerganov#2239)
  fix : remove extra files
  scripts : sync ggml-blas
  build : update make / cmake
  sync : ggml
  move BLAS to a separate backend (cont) (llama/6210)
  Vulkan Shader Refactor, Memory Debugging Option (llama/7947)
  scripts : stop sync whisper example from ggml
  cmake : fix sycl build (#0)
  ggml : remove OpenCL (#0)
  sycl : sync (#0)
  cuda : enable CUDA graphs (#0)
  talk-llama : sync llama.cpp
  cmake : fix CUDA build (#0)
  sync : ggml
  ggml : fix and optimize ppc64le (ggml/849)
  ...

.devops/main-cuda.Dockerfile

@@ -28,6 +28,8 @@ COPY .. .
 RUN make
 
 FROM ${BASE_CUDA_RUN_CONTAINER} AS runtime
+ENV CUDA_MAIN_VERSION=12.3
+ENV LD_LIBRARY_PATH /usr/local/cuda-${CUDA_MAIN_VERSION}/compat:$LD_LIBRARY_PATH
 WORKDIR /app
 
 RUN apt-get update && \