Merge remote-tracking branch 'ggerganov/master' into fix_decoding

* ggerganov/master: (447 commits)
  ruby : Add low-level methods to transcribe (ggml-org#2585)
  models : add `q8_0` models to `download-ggml-model.sh` (ggml-org#2589)
  ruby : Follow source tree change (ggml-org#2580)
  whisper : use backend registry (#0)
  ggml/sched : do not skip views in pre-assignments
  whisper : adapt to new ggml (wip)
  talk-llama : sync llama.cpp
  sync : ggml
  ggml : sync resolve (skip) (#0)
  Add required ggml-base and backend libs to cmake pkg (llama/10407)
  cuda : fix CUDA_FLAGS not being applied (llama/10403)
  sycl : Add option to set the SYCL architecture for all targets (llama/10266)
  vulkan: Optimize soft_max (llama/10301)
  sycl: Revert MUL_MAT_OP support changes (llama/10385)
  cuda : only use native when supported by cmake (llama/10389)
  vulkan: remove use of null initializer (llama/10372)
  metal : fox offset integer overflows in im2col (ggml/1015)
  Vulkan: Fix device info output format specifiers (llama/10366)
  metal : add `GGML_UNARY_OP_ELU` kernel (ggml/1018)
  CUDA: fix MMV kernel being used for FP16 src1 (llama/10357)
  ...

Author: bygreencn

.devops/cublas.Dockerfile

@@ -12,7 +12,7 @@ FROM ${BASE_CUDA_DEV_CONTAINER} as build
 ARG CUDA_DOCKER_ARCH=all
 
 RUN apt-get update && \
-    apt-get install -y build-essential git cmake
+    apt-get install -y build-essential git cmake libsdl2-dev
 
 WORKDIR /app
 
@@ -21,7 +21,7 @@ COPY . .
 # Set nvcc architecture
 ENV CUDA_DOCKER_ARCH=${CUDA_DOCKER_ARCH}
 # Enable cuBLAS
-ENV WHISPER_CUBLAS=1
+ENV GGML_CUDA=1
 
 RUN make
 

.devops/main-cuda.Dockerfile

@@ -14,10 +14,10 @@ ARG CUDA_DOCKER_ARCH=all
 # Set nvcc architecture
 ENV CUDA_DOCKER_ARCH=${CUDA_DOCKER_ARCH}
 # Enable cuBLAS
-ENV WHISPER_CUBLAS=1
+ENV GGML_CUDA=1
 
 RUN apt-get update && \
-    apt-get install -y build-essential \
+    apt-get install -y build-essential libsdl2-dev \
     && rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*
 
 # Ref: https://stackoverflow.com/a/53464012

.devops/main.Dockerfile

@@ -12,7 +12,7 @@ FROM ubuntu:22.04 AS runtime
 WORKDIR /app
 
 RUN apt-get update && \
-  apt-get install -y curl ffmpeg \
+  apt-get install -y curl ffmpeg libsdl2-dev \
   && rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*
 
 COPY --from=build /app /app

.github/workflows/bindings-go.yml

@@ -13,10 +13,10 @@ jobs:
   ubuntu-latest:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/setup-go@v3
+      - uses: actions/setup-go@v5
         with:
-          go-version: '^1.19'
-      - uses: actions/checkout@v1
+          go-version: '^1.23'
+      - uses: actions/checkout@v4
       - run: |
           cd bindings/go
           make test

.github/workflows/bindings-ruby.yml

@@ -3,20 +3,53 @@ on:
   push:
     paths:
       - bindings/ruby/**
-      - whisper.h
+      - src/**/*.c
+      - src/**/*.cpp
+      - src/**/*.h
+      - src/**/*.m
+      - src/**/*.metal
+      - include/**/*.c
+      - include/**/*.cpp
+      - include/**/*.h
+      - include/**/*.m
+      - include/**/*.metal
+      - ggml/**/*.c
+      - ggml/**/*.cpp
+      - ggml/**/*.h
+      - ggml/**/*.m
+      - ggml/**/*.metal
+      - scripts/get-flags.mk
+      - examples/dr_wav.h
   pull_request:
     paths:
       - bindings/ruby/**
-      - whisper.h
+      - src/**/*.c
+      - src/**/*.cpp
+      - src/**/*.h
+      - src/**/*.m
+      - src/**/*.metal
+      - include/**/*.c
+      - include/**/*.cpp
+      - include/**/*.h
+      - include/**/*.m
+      - include/**/*.metal
+      - ggml/**/*.c
+      - ggml/**/*.cpp
+      - ggml/**/*.h
+      - ggml/**/*.m
+      - ggml/**/*.metal
+      - scripts/get-flags.mk
+      - examples/dr_wav.h
 
 jobs:
   ubuntu-latest:
     runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: bindings/ruby
     steps:
       - uses: ruby/setup-ruby@v1
         with:
-          ruby-version: '3.0'
-      - uses: actions/checkout@v1
-      - run: |
-          cd bindings/ruby/ext
-          ruby extconf.rb && make
+          ruby-version: '3.1'
+      - uses: actions/checkout@v4
+      - run: rake test