vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'ggerganov:master' into server-ui-pr

Browse source
This commit is contained in:
Yazan Agha-Schrader 2024-05-30 08:28:26 +02:00 • committed by GitHub
commit 0d75e07bd9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 30 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

8
.devops/main-intel.Dockerfile
View file

@ -2,6 +2,14 @@ ARG ONEAPI_VERSION=2024.0.1-devel-ubuntu22.04
FROM intel/oneapi-basekit:$ONEAPI_VERSION as build FROM intel/oneapi-basekit:$ONEAPI_VERSION as build
RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | tee /usr/share/keyrings/intel-oneapi-archive-keyring.gpg > /dev/null && \
echo "deb [signed-by=/usr/share/keyrings/intel-oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main " | tee /etc/apt/sources.list.d/oneAPI.list && \
chmod 644 /usr/share/keyrings/intel-oneapi-archive-keyring.gpg && \
rm /etc/apt/sources.list.d/intel-graphics.list && \
wget -O- https://repositories.intel.com/graphics/intel-graphics.key | gpg --dearmor | tee /usr/share/keyrings/intel-graphics.gpg > /dev/null && \
echo "deb [arch=amd64,i386 signed-by=/usr/share/keyrings/intel-graphics.gpg] https://repositories.intel.com/graphics/ubuntu jammy arc" | tee /etc/apt/sources.list.d/intel.gpu.jammy.list && \
chmod 644 /usr/share/keyrings/intel-graphics.gpg
ARG LLAMA_SYCL_F16=OFF ARG LLAMA_SYCL_F16=OFF
RUN apt-get update && \ RUN apt-get update && \
apt-get install -y git apt-get install -y git

16
.devops/server-intel.Dockerfile
View file

@ -2,6 +2,14 @@ ARG ONEAPI_VERSION=2024.0.1-devel-ubuntu22.04
FROM intel/oneapi-basekit:$ONEAPI_VERSION as build FROM intel/oneapi-basekit:$ONEAPI_VERSION as build
RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | tee /usr/share/keyrings/intel-oneapi-archive-keyring.gpg > /dev/null && \
echo "deb [signed-by=/usr/share/keyrings/intel-oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main " | tee /etc/apt/sources.list.d/oneAPI.list && \
chmod 644 /usr/share/keyrings/intel-oneapi-archive-keyring.gpg && \
rm /etc/apt/sources.list.d/intel-graphics.list && \
wget -O- https://repositories.intel.com/graphics/intel-graphics.key | gpg --dearmor | tee /usr/share/keyrings/intel-graphics.gpg > /dev/null && \
echo "deb [arch=amd64,i386 signed-by=/usr/share/keyrings/intel-graphics.gpg] https://repositories.intel.com/graphics/ubuntu jammy arc" | tee /etc/apt/sources.list.d/intel.gpu.jammy.list && \
chmod 644 /usr/share/keyrings/intel-graphics.gpg
ARG LLAMA_SYCL_F16=OFF ARG LLAMA_SYCL_F16=OFF
RUN apt-get update && \ RUN apt-get update && \
apt-get install -y git libcurl4-openssl-dev apt-get install -y git libcurl4-openssl-dev
@ -19,6 +27,14 @@ RUN if [ "${LLAMA_SYCL_F16}" = "ON" ]; then \
FROM intel/oneapi-basekit:$ONEAPI_VERSION as runtime FROM intel/oneapi-basekit:$ONEAPI_VERSION as runtime
RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | tee /usr/share/keyrings/intel-oneapi-archive-keyring.gpg > /dev/null && \
echo "deb [signed-by=/usr/share/keyrings/intel-oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main " | tee /etc/apt/sources.list.d/oneAPI.list && \
chmod 644 /usr/share/keyrings/intel-oneapi-archive-keyring.gpg && \
rm /etc/apt/sources.list.d/intel-graphics.list && \
wget -O- https://repositories.intel.com/graphics/intel-graphics.key | gpg --dearmor | tee /usr/share/keyrings/intel-graphics.gpg > /dev/null && \
echo "deb [arch=amd64,i386 signed-by=/usr/share/keyrings/intel-graphics.gpg] https://repositories.intel.com/graphics/ubuntu jammy arc" | tee /etc/apt/sources.list.d/intel.gpu.jammy.list && \
chmod 644 /usr/share/keyrings/intel-graphics.gpg
RUN apt-get update && \ RUN apt-get update && \
apt-get install -y libcurl4-openssl-dev apt-get install -y libcurl4-openssl-dev

5
.github/workflows/docker.yml vendored
View file

@ -42,9 +42,8 @@ jobs:
- { tag: "light-rocm", dockerfile: ".devops/main-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" } - { tag: "light-rocm", dockerfile: ".devops/main-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" }
- { tag: "full-rocm", dockerfile: ".devops/full-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" } - { tag: "full-rocm", dockerfile: ".devops/full-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" }
- { tag: "server-rocm", dockerfile: ".devops/server-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" } - { tag: "server-rocm", dockerfile: ".devops/server-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" }
# TODO: Disabled due to build issues https://github.com/ggerganov/llama.cpp/issues/7507 - { tag: "light-intel", dockerfile: ".devops/main-intel.Dockerfile", platforms: "linux/amd64" }
#- { tag: "light-intel", dockerfile: ".devops/main-intel.Dockerfile", platforms: "linux/amd64" } - { tag: "server-intel", dockerfile: ".devops/server-intel.Dockerfile", platforms: "linux/amd64" }
#- { tag: "server-intel", dockerfile: ".devops/server-intel.Dockerfile", platforms: "linux/amd64" }
steps: steps:
- name: Check out the repo - name: Check out the repo
uses: actions/checkout@v4 uses: actions/checkout@v4

4
gguf-py/scripts/gguf-new-metadata.py
View file

@ -144,6 +144,7 @@ def main() -> None:
parser.add_argument("--general-description", type=str, help="The models general.description", metavar='"Description ..."') parser.add_argument("--general-description", type=str, help="The models general.description", metavar='"Description ..."')
parser.add_argument("--chat-template", type=str, help="Chat template string (or JSON string containing templates)", metavar='"{% ... %} ..."') parser.add_argument("--chat-template", type=str, help="Chat template string (or JSON string containing templates)", metavar='"{% ... %} ..."')
parser.add_argument("--chat-template-config", type=Path, help="Config file containing chat template(s)", metavar='tokenizer_config.json') parser.add_argument("--chat-template-config", type=Path, help="Config file containing chat template(s)", metavar='tokenizer_config.json')
parser.add_argument("--pre-tokenizer", type=str, help="The models tokenizer.ggml.pre", metavar='"pre tokenizer"')
parser.add_argument("--remove-metadata", action="append", type=str, help="Remove metadata (by key name) from output model", metavar='general.url') parser.add_argument("--remove-metadata", action="append", type=str, help="Remove metadata (by key name) from output model", metavar='general.url')
parser.add_argument("--special-token", action="append", type=str, help="Special token by value", nargs=2, metavar=(' | '.join(token_names.keys()), '"<token>"')) parser.add_argument("--special-token", action="append", type=str, help="Special token by value", nargs=2, metavar=(' | '.join(token_names.keys()), '"<token>"'))
parser.add_argument("--special-token-by-id", action="append", type=str, help="Special token by id", nargs=2, metavar=(' | '.join(token_names.keys()), '0')) parser.add_argument("--special-token-by-id", action="append", type=str, help="Special token by id", nargs=2, metavar=(' | '.join(token_names.keys()), '0'))
@ -172,6 +173,9 @@ def main() -> None:
if template: if template:
new_metadata[gguf.Keys.Tokenizer.CHAT_TEMPLATE] = MetadataDetails(gguf.GGUFValueType.STRING, template) new_metadata[gguf.Keys.Tokenizer.CHAT_TEMPLATE] = MetadataDetails(gguf.GGUFValueType.STRING, template)
if args.pre_tokenizer:
new_metadata[gguf.Keys.Tokenizer.PRE] = MetadataDetails(gguf.GGUFValueType.STRING, args.pre_tokenizer)
if remove_metadata: if remove_metadata:
logger.warning('*** Warning *** Warning *** Warning **') logger.warning('*** Warning *** Warning *** Warning **')
logger.warning('* Most metadata is required for a fully functional GGUF file,') logger.warning('* Most metadata is required for a fully functional GGUF file,')