Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
53 commits
Select commit Hold shift + click to select a range
ab7df17
ggml-cpu : fix ggml_graph_compute_thread did not terminate on abort. …
issixx Jan 17, 2025
eba54c7
ggml : add option to not print stack on abort (ggml/1081)
WilliamTambellini Jan 23, 2025
bda3451
SYCL: Add gated linear attention kernel (llama/11175)
qnixsynapse Jan 15, 2025
11eb7f4
RoPE: fix back, CUDA support for back + noncont. (llama/11240)
JohannesGaessler Jan 15, 2025
3a1f833
fix: ggml: fix vulkan-shaders-gen build (llama/10448)
sparkleholic Jan 15, 2025
a89b132
vulkan: scale caching for k quants + misc fixes (llama/11081)
netrunnereve Jan 15, 2025
220d0b3
ggml: aarch64: implement SVE kernels for q4_K_q8_K vector dot (llama/…
fj-y-saito Jan 16, 2025
0965fe9
CUDA: backwards pass for misc. ops, add tests (llama/11257)
JohannesGaessler Jan 16, 2025
2e452fe
vulkan: optimize coopmat2 q2_k dequant function (llama/11130)
jeffbolznv Jan 16, 2025
aa8adfa
vulkan: optimize coopmat2 q4_k/q5_k dequant functions. (llama/11206)
jeffbolznv Jan 16, 2025
b956395
vulkan: support copy from f32 to q4_0/q4_1/q5_0/q5_1/q8_0/iq4_nl (lla…
jeffbolznv Jan 16, 2025
315a224
rpc : early register backend devices (llama/11262)
rgerganov Jan 17, 2025
529b36e
vulkan: fix coopmat2 flash attention for non-contiguous inputs (llama…
jeffbolznv Jan 18, 2025
1213918
cmake : add sanitizer flags for llama.cpp (llama/11279)
ggerganov Jan 18, 2025
0b94a0b
SYCL: Introducing memory host pool (llama/11251)
s-Nick Jan 19, 2025
9cf3fdd
vulkan: fix coopmat2 validation failures (llama/11284)
jeffbolznv Jan 20, 2025
f23199c
metal : fix out-of-bounds write (llama/11314)
ggerganov Jan 21, 2025
939144c
rpc : better caching of the base buffer pointer (llama/11331)
rgerganov Jan 21, 2025
596288c
vulkan: fix diag_mask_inf (llama/11323)
jeffbolznv Jan 23, 2025
7a137f9
vulkan: sort shaders for more deterministic binary (llama/11315)
jeffbolznv Jan 23, 2025
f282673
Vulkan-run-test: fix mmq_wg_denoms (llama/11343)
AMD-dwang Jan 23, 2025
276cc41
cmake : avoid -march=native when reproducible build is wanted (llama/…
bmwiedemann Jan 24, 2025
4e6471e
CPU/CUDA: fix (GQA) mul mat back, add CUDA support (llama/11380)
JohannesGaessler Jan 24, 2025
9789f26
rocBLAS: Avoid fp32->fp16->fp32 conversion on cdna (llama/11356)
IMbackK Jan 24, 2025
c9a1d35
CUDA: fix FP16 cuBLAS GEMM (llama/11396)
JohannesGaessler Jan 24, 2025
41cd5db
hip : Add hipGraph and VMM support to ROCM (llama/11362)
IMbackK Jan 24, 2025
d537633
Hip: disable VMM on hip as it seams that it dosent work in some confi…
IMbackK Jan 25, 2025
3f911fa
vulkan: compile shaders on-demand (llama/11406)
jeffbolznv Jan 25, 2025
36473b8
cmake: add ggml find package (llama/11369)
bandoti Jan 26, 2025
48ca09d
metal : use residency sets (llama/11427)
ggerganov Jan 26, 2025
94dbfb2
metal: Handle null returned from MTLCreateSystemDefaultDevice() (llam…
Jan 27, 2025
cd000b5
AMD: parse the architecture as supplied by gcnArchName (llama/11244)
Haus1 Jan 27, 2025
a60c461
SYCL : SOFTMAX F16 mask support and other fixes (llama/11261)
qnixsynapse Jan 28, 2025
3a06dc4
cmake : don't fail on `GGML_CPU=OFF` (llama/11457)
someone13574 Jan 28, 2025
7664f6c
HIP: Only call rocblas_initialize on rocblas versions with the multip…
sARY77 Jan 28, 2025
76355dd
HIP: Supress transformation warning in softmax.cu
IMbackK Jan 28, 2025
b2c7108
vulkan: Catch pipeline creation failure and print an error message (l…
jeffbolznv Jan 29, 2025
2178b0c
vulkan: implement initial support for IQ2 and IQ3 quantizations (llam…
remyoudompheng Jan 29, 2025
0ef996a
CUDA/HIP: add warp_size to cuda_device_info
IMbackK Jan 29, 2025
1c03647
HIP: Prepare reduction operators for wave 64
IMbackK Jan 29, 2025
69bbc39
HIP: require at least HIP 5.5
IMbackK Jan 29, 2025
f157854
`ci`: use sccache on windows instead of ccache (llama/11545)
ochafik Jan 31, 2025
8b531ba
CUDA: use mma PTX instructions for FlashAttention (llama/11583)
JohannesGaessler Feb 2, 2025
86bc5ad
HIP: add GGML_CUDA_CC_IS_* for amd familys as increasing cc archtectu…
IMbackK Feb 2, 2025
1140023
CUDA/HIP: add support for selectable warp size to mmv (llama/11519)
IMbackK Feb 2, 2025
4ca2fcd
HIP: fix flash_attn_stream_k_fixup warning (llama/11604)
JohannesGaessler Feb 2, 2025
f2fb21f
CUDA: fix Volta FlashAttention logic (llama/11615)
JohannesGaessler Feb 3, 2025
4e570fd
scripts : fix sync paths
ggerganov Feb 3, 2025
2542c1a
sync : ggml
ggerganov Feb 3, 2025
6086e98
cmake : sync cmake scripts
ggerganov Feb 3, 2025
94bad05
ci : use ubuntu-22.04 instead of ubuntu-latest
ggerganov Feb 3, 2025
cbf347b
ci : install git
ggerganov Feb 3, 2025
0ab5ba0
ci : more git
ggerganov Feb 3, 2025
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .devops/cublas.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -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 libsdl2-dev wget
apt-get install -y build-essential git cmake libsdl2-dev wget git

WORKDIR /app

Expand Down
4 changes: 2 additions & 2 deletions .devops/main-cuda.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ ENV CUDA_DOCKER_ARCH=${CUDA_DOCKER_ARCH}
ENV GGML_CUDA=1

RUN apt-get update && \
apt-get install -y build-essential libsdl2-dev wget cmake \
apt-get install -y build-essential libsdl2-dev wget cmake git \
&& rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*

# Ref: https://stackoverflow.com/a/53464012
Expand All @@ -33,7 +33,7 @@ ENV LD_LIBRARY_PATH /usr/local/cuda-${CUDA_MAIN_VERSION}/compat:$LD_LIBRARY_PATH
WORKDIR /app

RUN apt-get update && \
apt-get install -y curl ffmpeg wget cmake \
apt-get install -y curl ffmpeg wget cmake git \
&& rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*

COPY --from=build /app /app
Expand Down
4 changes: 2 additions & 2 deletions .devops/main.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@ FROM ubuntu:22.04 AS build
WORKDIR /app

RUN apt-get update && \
apt-get install -y build-essential wget cmake \
apt-get install -y build-essential wget cmake git \
&& rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*

COPY .. .
Expand All @@ -12,7 +12,7 @@ FROM ubuntu:22.04 AS runtime
WORKDIR /app

RUN apt-get update && \
apt-get install -y curl ffmpeg libsdl2-dev wget cmake \
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
Expand Down
4 changes: 2 additions & 2 deletions .github/workflows/bindings-go.yml
Original file line number Diff line number Diff line change
Expand Up @@ -10,8 +10,8 @@ on:
- whisper.h

jobs:
ubuntu-latest:
runs-on: ubuntu-latest
ubuntu-22:
runs-on: ubuntu-22.04
steps:
- uses: actions/setup-go@v5
with:
Expand Down
4 changes: 2 additions & 2 deletions .github/workflows/bindings-ruby.yml
Original file line number Diff line number Diff line change
Expand Up @@ -42,8 +42,8 @@ on:
- examples/dr_wav.h

jobs:
ubuntu-latest:
runs-on: ubuntu-latest
ubuntu-22:
runs-on: ubuntu-22.04
defaults:
run:
working-directory: bindings/ruby
Expand Down
71 changes: 36 additions & 35 deletions .github/workflows/build.yml
Original file line number Diff line number Diff line change
Expand Up @@ -16,8 +16,8 @@ env:
VCPKG_BINARY_SOURCES: "clear;x-gha,readwrite"

jobs:
ubuntu-latest:
runs-on: ubuntu-latest
ubuntu-22:
runs-on: ubuntu-22.04

strategy:
fail-fast: false
Expand All @@ -38,12 +38,12 @@ jobs:
-w /workspace ${{ env.ubuntu_image }} /bin/sh -c '
set -e
apt update
apt install -y build-essential libsdl2-dev cmake
apt install -y build-essential libsdl2-dev cmake git
cmake -B build
cmake --build build --config Release -j $(nproc)'

ubuntu-latest-arm64:
runs-on: ubuntu-latest
ubuntu-22-arm64:
runs-on: ubuntu-22.04

strategy:
fail-fast: false
Expand All @@ -64,12 +64,12 @@ jobs:
-w /workspace ${{ env.ubuntu_image }} /bin/sh -c '
set -e
apt update
apt install -y build-essential libsdl2-dev cmake
apt install -y build-essential libsdl2-dev cmake git
cmake -B build -DGGML_NATIVE=OFF -DGGML_CPU_ARM_ARCH=armv8-a
cmake --build build --config Release -j $(nproc)'

ubuntu-latest-arm-v7:
runs-on: ubuntu-latest
ubuntu-22-arm-v7:
runs-on: ubuntu-22.04

strategy:
fail-fast: false
Expand All @@ -90,7 +90,7 @@ jobs:
-w /workspace ${{ env.ubuntu_image }} /bin/sh -c '
set -e
apt update
apt install -y build-essential libsdl2-dev cmake
apt install -y build-essential libsdl2-dev cmake git
cmake -B build -DGGML_NATIVE=OFF -DGGML_CPU_ARM_ARCH=armv7-a+fp
cmake --build build --config Release -j $(nproc)'

Expand Down Expand Up @@ -129,8 +129,8 @@ jobs:
# cmake -B build
# cmake --build build --config Release

ubuntu-latest-gcc:
runs-on: ubuntu-latest
ubuntu-22-gcc:
runs-on: ubuntu-22.04

strategy:
fail-fast: false
Expand All @@ -152,13 +152,13 @@ jobs:
-w /workspace ${{ env.ubuntu_image }} /bin/sh -c '
set -e
apt update
apt install -y build-essential cmake libsdl2-dev
apt install -y build-essential cmake libsdl2-dev git
cmake . -DWHISPER_SDL2=ON -DCMAKE_BUILD_TYPE=${{ matrix.build }}
make
ctest -L gh --output-on-failure'

ubuntu-latest-gcc-arm64:
runs-on: ubuntu-latest
ubuntu-22-gcc-arm64:
runs-on: ubuntu-22.04

strategy:
fail-fast: false
Expand All @@ -180,13 +180,13 @@ jobs:
-w /workspace ${{ env.ubuntu_image }} /bin/sh -c '
set -e
apt update
apt install -y build-essential cmake libsdl2-dev
apt install -y build-essential cmake libsdl2-dev git
cmake . -DWHISPER_SDL2=ON -DCMAKE_BUILD_TYPE=${{ matrix.build }} -DGGML_NATIVE=OFF -DGGML_CPU_ARM_ARCH=armv8-a
make
ctest -L gh --output-on-failure'

ubuntu-latest-gcc-arm-v7:
runs-on: ubuntu-latest
ubuntu-22-gcc-arm-v7:
runs-on: ubuntu-22.04

strategy:
fail-fast: false
Expand All @@ -208,13 +208,13 @@ jobs:
-w /workspace ${{ env.ubuntu_image }} /bin/sh -c '
set -e
apt update
apt install -y build-essential cmake libsdl2-dev
apt install -y build-essential cmake libsdl2-dev git
cmake . -DWHISPER_SDL2=ON -DCMAKE_BUILD_TYPE=${{ matrix.build }} -DGGML_NATIVE=OFF -DGGML_CPU_ARM_ARCH=armv7-a+fp
make
ctest -L gh --output-on-failure'

ubuntu-latest-clang:
runs-on: ubuntu-latest
ubuntu-22-clang:
runs-on: ubuntu-22.04

strategy:
fail-fast: false
Expand All @@ -239,13 +239,13 @@ jobs:
-w /workspace ${{ env.ubuntu_image }} /bin/sh -c '
set -e
apt update
apt install -y clang build-essential cmake libsdl2-dev
apt install -y clang build-essential cmake libsdl2-dev git
cmake . -DWHISPER_SDL2=ON -DCMAKE_BUILD_TYPE=${{ matrix.build }} -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_COMPILER=clang
make
ctest -L gh --output-on-failure'

ubuntu-latest-gcc-sanitized:
runs-on: ubuntu-latest
ubuntu-22-gcc-sanitized:
runs-on: ubuntu-22.04

strategy:
fail-fast: false
Expand All @@ -267,7 +267,7 @@ jobs:
-w /workspace ${{ env.ubuntu_image }} /bin/sh -c '
set -e
apt update
apt install -y build-essential cmake
apt install -y build-essential cmake git
cmake . -DCMAKE_BUILD_TYPE=Debug -DWHISPER_SANITIZE_${{ matrix.sanitizer }}=ON
make
ctest -L gh --output-on-failure'
Expand Down Expand Up @@ -302,12 +302,12 @@ jobs:
shell: bash
run: |
sudo apt update
sudo apt install intel-oneapi-compiler-dpcpp-cpp
sudo apt install intel-oneapi-compiler-dpcpp-cpp git

- name: install oneAPI MKL library
shell: bash
run: |
sudo apt install intel-oneapi-mkl-devel
sudo apt install intel-oneapi-mkl-devel git

- name: Clone
id: checkout
Expand Down Expand Up @@ -352,7 +352,7 @@ jobs:
shell: bash
run: |
sudo apt update
sudo apt install intel-oneapi-compiler-dpcpp-cpp
sudo apt install intel-oneapi-compiler-dpcpp-cpp git

- name: install oneAPI MKL library
shell: bash
Expand Down Expand Up @@ -393,6 +393,7 @@ jobs:
msystem: ${{matrix.sys}}
install: >-
base-devel
git
mingw-w64-${{matrix.env}}-toolchain
mingw-w64-${{matrix.env}}-cmake
mingw-w64-${{matrix.env}}-SDL2
Expand Down Expand Up @@ -584,7 +585,7 @@ jobs:
7z x sdl2.zip
echo "SDL2_DIR=${{ github.workspace }}\SDL2-${{ matrix.sdl2_ver }}\cmake" | Out-File -FilePath $env:GITHUB_ENV -Append
echo "${{ github.workspace }}\SDL2-${{ matrix.sdl2_ver }}\cmake" > SDL2_PATH.txt

- name: Configure CMake
shell: cmd
run: |
Expand All @@ -594,16 +595,16 @@ jobs:
-DCMAKE_CUDA_ARCHITECTURES=all ^
-DWHISPER_SDL2=${{ matrix.sdl2 }} ^
-DSDL2_DIR="%SDL2_DIR%"

- name: Build Project
shell: cmd
run: |
cd ./build
cmake --build . --config ${{ matrix.build }}
cmake --build . --config ${{ matrix.build }}

- name: Copy CUDA DLLs
run: |
Get-ChildItem "${{ steps.cuda-toolkit.outputs.CUDA_PATH }}/bin/" -Filter "*.dll" |
Get-ChildItem "${{ steps.cuda-toolkit.outputs.CUDA_PATH }}/bin/" -Filter "*.dll" |
Copy-Item -Destination "build/bin/${{ matrix.build }}"

- name: Copy SDL2.dll
Expand All @@ -617,7 +618,7 @@ jobs:
path: build/bin/${{ matrix.build }}

emscripten:
runs-on: ubuntu-latest
runs-on: ubuntu-22.04

strategy:
matrix:
Expand Down Expand Up @@ -684,7 +685,7 @@ jobs:
run: xcodebuild -project examples/whisper.swiftui/whisper.swiftui.xcodeproj -scheme WhisperCppDemo -configuration ${{ matrix.build }} -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' build

android:
runs-on: ubuntu-latest
runs-on: ubuntu-22.04

steps:
- name: Clone
Expand Down Expand Up @@ -714,7 +715,7 @@ jobs:

# TODO: disable because of following fail: https://github.com/ggerganov/whisper.cpp/actions/runs/11019444420/job/30627193602
# android_java:
# runs-on: ubuntu-latest
# runs-on: ubuntu-22.04
#
# steps:
# - name: Clone
Expand Down Expand Up @@ -783,7 +784,7 @@ jobs:
# PGP_PASSPHRASE: ${{ secrets.GPG_PASSPHRASE }}

quantize:
runs-on: ubuntu-latest
runs-on: ubuntu-22.04

steps:
- name: Clone
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/docker.yml
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ jobs:
name: Push Docker image to Docker Hub
if: github.event.pull_request.draft == false

runs-on: ubuntu-latest
runs-on: ubuntu-22.04
env:
COMMIT_SHA: ${{ github.sha }}
strategy:
Expand Down
6 changes: 3 additions & 3 deletions .github/workflows/examples.yml
Original file line number Diff line number Diff line change
Expand Up @@ -10,8 +10,8 @@ on:
- whisper.h

jobs:
addon_node-ubuntu-latest:
runs-on: ubuntu-latest
addon_node-ubuntu-22:
runs-on: ubuntu-22.04
strategy:
matrix:
node-version: [ 16.x, 18.x ]
Expand All @@ -22,7 +22,7 @@ jobs:
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install build-essential
sudo apt-get install build-essential git
sudo apt-get install cmake
sudo apt-get install libsdl2-dev

Expand Down
Loading
Loading