Skip to content

Commit a3904c0

Browse files
CISCCISC
authored
Merge branch 'master' into cisc/bailingmoe2
2 parents 6ee701d + 4807e8f commit a3904c0

File tree

284 files changed

+12910
-6476
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

284 files changed

+12910
-6476
lines changed

‎.clang-tidy‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -17,6 +17,7 @@ Checks: >
1717
clang-analyzer-*,
1818
-clang-analyzer-security.insecureAPI.DeprecatedOrUnsafeBufferHandling,
1919
performance-*,
20+
-performance-enum-size,
2021
portability-*,
2122
-portability-simd-intrinsics,
2223
misc-*,

‎.devops/musa.Dockerfile‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,10 +1,10 @@
11
ARG UBUNTU_VERSION=22.04
22
# This needs to generally match the container host's environment.
3-
ARG MUSA_VERSION=rc4.2.0
3+
ARG MUSA_VERSION=rc4.3.0
44
# Target the MUSA build image
5-
ARG BASE_MUSA_DEV_CONTAINER=mthreads/musa:${MUSA_VERSION}-devel-ubuntu${UBUNTU_VERSION}-amd64
5+
ARG BASE_MUSA_DEV_CONTAINER=sh-harbor.mthreads.com/haive/mthreads/musa:${MUSA_VERSION}-devel-ubuntu${UBUNTU_VERSION}-amd64
66

7-
ARG BASE_MUSA_RUN_CONTAINER=mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}-amd64
7+
ARG BASE_MUSA_RUN_CONTAINER=sh-harbor.mthreads.com/haive/mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}-amd64
88

99
FROM ${BASE_MUSA_DEV_CONTAINER} AS build
1010

‎.devops/s390x.Dockerfile‎

Lines changed: 123 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,123 @@
1+
ARG GCC_VERSION=15.2.0
2+
ARG UBUNTU_VERSION=24.04
3+
4+
### Build Llama.cpp stage
5+
FROM gcc:${GCC_VERSION} AS build
6+
7+
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
8+
--mount=type=cache,target=/var/lib/apt/lists,sharing=locked \
9+
apt update -y && \
10+
apt upgrade -y && \
11+
apt install -y --no-install-recommends \
12+
git cmake ccache ninja-build \
13+
# WARNING: Do not use libopenblas-openmp-dev. libopenblas-dev is faster.
14+
libopenblas-dev libcurl4-openssl-dev && \
15+
rm -rf /var/lib/apt/lists/*
16+
17+
WORKDIR /app
18+
COPY . .
19+
20+
RUN --mount=type=cache,target=/root/.ccache \
21+
--mount=type=cache,target=/app/build \
22+
cmake -S . -B build -G Ninja \
23+
-DCMAKE_BUILD_TYPE=Release \
24+
-DCMAKE_C_COMPILER_LAUNCHER=ccache \
25+
-DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
26+
-DLLAMA_BUILD_TESTS=OFF \
27+
-DGGML_BACKEND_DL=OFF \
28+
-DGGML_NATIVE=OFF \
29+
-DGGML_BLAS=ON \
30+
-DGGML_BLAS_VENDOR=OpenBLAS && \
31+
cmake --build build --config Release -j $(nproc) && \
32+
cmake --install build --prefix /opt/llama.cpp
33+
34+
COPY *.py /opt/llama.cpp/bin
35+
COPY .devops/tools.sh /opt/llama.cpp/bin
36+
37+
COPY gguf-py /opt/llama.cpp/gguf-py
38+
COPY requirements.txt /opt/llama.cpp/gguf-py
39+
COPY requirements /opt/llama.cpp/gguf-py/requirements
40+
41+
42+
### Collect all llama.cpp binaries, libraries and distro libraries
43+
FROM scratch AS collector
44+
45+
# Copy llama.cpp binaries and libraries
46+
COPY --from=build /opt/llama.cpp/bin /llama.cpp/bin
47+
COPY --from=build /opt/llama.cpp/lib /llama.cpp/lib
48+
COPY --from=build /opt/llama.cpp/gguf-py /llama.cpp/gguf-py
49+
50+
51+
### Base image
52+
FROM ubuntu:${UBUNTU_VERSION} AS base
53+
54+
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
55+
--mount=type=cache,target=/var/lib/apt/lists,sharing=locked \
56+
apt update -y && \
57+
apt install -y --no-install-recommends \
58+
# WARNING: Do not use libopenblas-openmp-dev. libopenblas-dev is faster.
59+
# See: https://github.com/ggml-org/llama.cpp/pull/15915#issuecomment-3317166506
60+
curl libgomp1 libopenblas-dev && \
61+
apt autoremove -y && \
62+
apt clean -y && \
63+
rm -rf /tmp/* /var/tmp/* && \
64+
find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete && \
65+
find /var/cache -type f -delete
66+
67+
# Copy llama.cpp libraries
68+
COPY --from=collector /llama.cpp/lib /usr/lib/s390x-linux-gnu
69+
70+
71+
### Full
72+
FROM base AS full
73+
74+
ENV PATH="/root/.cargo/bin:${PATH}"
75+
WORKDIR /app
76+
77+
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
78+
--mount=type=cache,target=/var/lib/apt/lists,sharing=locked \
79+
apt update -y && \
80+
apt install -y \
81+
git cmake libjpeg-dev \
82+
python3 python3-pip python3-dev && \
83+
apt autoremove -y && \
84+
apt clean -y && \
85+
rm -rf /tmp/* /var/tmp/* && \
86+
find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete && \
87+
find /var/cache -type f -delete
88+
89+
RUN curl https://sh.rustup.rs -sSf | bash -s -- -y
90+
91+
COPY --from=collector /llama.cpp/bin /app
92+
COPY --from=collector /llama.cpp/gguf-py /app/gguf-py
93+
94+
RUN pip install --no-cache-dir --break-system-packages \
95+
-r /app/gguf-py/requirements.txt
96+
97+
ENTRYPOINT [ "/app/tools.sh" ]
98+
99+
100+
### CLI Only
101+
FROM base AS light
102+
103+
WORKDIR /llama.cpp/bin
104+
105+
# Copy llama.cpp binaries and libraries
106+
COPY --from=collector /llama.cpp/bin/llama-cli /llama.cpp/bin
107+
108+
ENTRYPOINT [ "/llama.cpp/bin/llama-cli" ]
109+
110+
111+
### Server
112+
FROM base AS server
113+
114+
ENV LLAMA_ARG_HOST=0.0.0.0
115+
116+
WORKDIR /llama.cpp/bin
117+
118+
# Copy llama.cpp binaries and libraries
119+
COPY --from=collector /llama.cpp/bin/llama-server /llama.cpp/bin
120+
121+
EXPOSE 8080
122+
123+
ENTRYPOINT [ "/llama.cpp/bin/llama-server" ]

‎.github/workflows/build-linux-cross.yml‎

Lines changed: 0 additions & 91 deletions
Original file line numberDiff line numberDiff line change
@@ -141,97 +141,6 @@ jobs:
141141

142142
# cmake --build build --config Release -j $(nproc)
143143

144-
ubuntu-24-ppc64el-cpu-cross:
145-
runs-on: ubuntu-24.04
146-
147-
steps:
148-
- uses: actions/checkout@v4
149-
- name: Setup PowerPC64le
150-
run: |
151-
sudo dpkg --add-architecture ppc64el
152-
153-
# Add arch-specific repositories for non-amd64 architectures
154-
cat << EOF | sudo tee /etc/apt/sources.list.d/ppc64el-ports.list
155-
deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble main universe
156-
deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble-updates main universe
157-
deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble-security main universe
158-
deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble-backports main universe
159-
EOF
160-
161-
sudo apt-get update || true ;# Prevent failure due to missing URLs.
162-
163-
sudo apt-get install -y --no-install-recommends \
164-
build-essential \
165-
gcc-14-powerpc64le-linux-gnu \
166-
g++-14-powerpc64le-linux-gnu
167-
168-
- name: Build
169-
run: |
170-
cmake -B build -DLLAMA_CURL=OFF \
171-
-DCMAKE_BUILD_TYPE=Release \
172-
-DGGML_OPENMP=OFF \
173-
-DLLAMA_BUILD_EXAMPLES=ON \
174-
-DLLAMA_BUILD_TOOLS=ON \
175-
-DLLAMA_BUILD_TESTS=OFF \
176-
-DCMAKE_SYSTEM_NAME=Linux \
177-
-DCMAKE_SYSTEM_PROCESSOR=ppc64 \
178-
-DCMAKE_C_COMPILER=powerpc64le-linux-gnu-gcc-14 \
179-
-DCMAKE_CXX_COMPILER=powerpc64le-linux-gnu-g++-14 \
180-
-DCMAKE_POSITION_INDEPENDENT_CODE=ON \
181-
-DCMAKE_FIND_ROOT_PATH=/usr/lib/powerpc64le-linux-gnu \
182-
-DCMAKE_FIND_ROOT_PATH_MODE_PROGRAM=NEVER \
183-
-DCMAKE_FIND_ROOT_PATH_MODE_LIBRARY=ONLY \
184-
-DCMAKE_FIND_ROOT_PATH_MODE_INCLUDE=BOTH
185-
186-
cmake --build build --config Release -j $(nproc)
187-
188-
# ubuntu-24-ppc64el-vulkan-cross:
189-
# runs-on: ubuntu-24.04
190-
191-
# steps:
192-
# - uses: actions/checkout@v4
193-
# - name: Setup PowerPC64le
194-
# run: |
195-
# sudo dpkg --add-architecture ppc64el
196-
197-
# # Add arch-specific repositories for non-amd64 architectures
198-
# cat << EOF | sudo tee /etc/apt/sources.list.d/ppc64el-ports.list
199-
# deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble main universe
200-
# deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble-updates main universe
201-
# deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble-security main universe
202-
# deb [arch=ppc64el] http://ports.ubuntu.com/ubuntu-ports/ noble-backports main universe
203-
# EOF
204-
205-
# sudo apt-get update || true ;# Prevent failure due to missing URLs.
206-
207-
# sudo apt-get install -y --no-install-recommends \
208-
# build-essential \
209-
# glslc \
210-
# gcc-14-powerpc64le-linux-gnu \
211-
# g++-14-powerpc64le-linux-gnu \
212-
# libvulkan-dev:ppc64el
213-
214-
# - name: Build
215-
# run: |
216-
# cmake -B build -DLLAMA_CURL=OFF \
217-
# -DCMAKE_BUILD_TYPE=Release \
218-
# -DGGML_VULKAN=ON \
219-
# -DGGML_OPENMP=OFF \
220-
# -DLLAMA_BUILD_EXAMPLES=ON \
221-
# -DLLAMA_BUILD_TOOLS=ON \
222-
# -DLLAMA_BUILD_TESTS=OFF \
223-
# -DCMAKE_SYSTEM_NAME=Linux \
224-
# -DCMAKE_SYSTEM_PROCESSOR=ppc64 \
225-
# -DCMAKE_C_COMPILER=powerpc64le-linux-gnu-gcc-14 \
226-
# -DCMAKE_CXX_COMPILER=powerpc64le-linux-gnu-g++-14 \
227-
# -DCMAKE_POSITION_INDEPENDENT_CODE=ON \
228-
# -DCMAKE_FIND_ROOT_PATH=/usr/lib/powerpc64le-linux-gnu \
229-
# -DCMAKE_FIND_ROOT_PATH_MODE_PROGRAM=NEVER \
230-
# -DCMAKE_FIND_ROOT_PATH_MODE_LIBRARY=ONLY \
231-
# -DCMAKE_FIND_ROOT_PATH_MODE_INCLUDE=BOTH
232-
233-
# cmake --build build --config Release -j $(nproc)
234-
235144
debian-13-loongarch64-cpu-cross:
236145
runs-on: ubuntu-24.04
237146
container: debian@sha256:653dfb9f86c3782e8369d5f7d29bb8faba1f4bff9025db46e807fa4c22903671

0 commit comments

Comments
 (0)