Skip to content

Commit 85db22d

Browse files
ngxsonngxson
committed
Merge branch 'master' into xsn/control-vector-generator
2 parents da6babd + 14f8352 commit 85db22d

File tree

325 files changed

+118508
-51365
lines changed

Some content is hidden

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

325 files changed

+118508
-51365
lines changed

‎.devops/full-cuda.Dockerfile

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -12,7 +12,7 @@ FROM ${BASE_CUDA_DEV_CONTAINER} as build
1212
ARG CUDA_DOCKER_ARCH=all
1313

1414
RUN apt-get update && \
15-
apt-get install -y build-essential python3 python3-pip git libcurl4-openssl-dev
15+
apt-get install -y build-essential python3 python3-pip git libcurl4-openssl-dev libgomp1
1616

1717
COPY requirements.txt requirements.txt
1818
COPY requirements requirements
@@ -31,6 +31,6 @@ ENV LLAMA_CUDA=1
3131
# Enable cURL
3232
ENV LLAMA_CURL=1
3333

34-
RUN make
34+
RUN make -j$(nproc)
3535

3636
ENTRYPOINT ["/app/.devops/tools.sh"]

‎.devops/full-rocm.Dockerfile

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -45,6 +45,6 @@ ENV LLAMA_CURL=1
4545
RUN apt-get update && \
4646
apt-get install -y libcurl4-openssl-dev
4747

48-
RUN make
48+
RUN make -j$(nproc)
4949

5050
ENTRYPOINT ["/app/.devops/tools.sh"]

‎.devops/full.Dockerfile

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ ARG UBUNTU_VERSION=22.04
33
FROM ubuntu:$UBUNTU_VERSION as build
44

55
RUN apt-get update && \
6-
apt-get install -y build-essential python3 python3-pip git libcurl4-openssl-dev
6+
apt-get install -y build-essential python3 python3-pip git libcurl4-openssl-dev libgomp1
77

88
COPY requirements.txt requirements.txt
99
COPY requirements requirements
@@ -18,7 +18,7 @@ COPY . .
1818
ENV LLAMA_CURL=1
1919

2020

21-
RUN make
21+
RUN make -j$(nproc)
2222

2323
ENV LC_ALL=C.utf8
2424

‎.devops/main-cuda.Dockerfile

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -23,10 +23,13 @@ ENV CUDA_DOCKER_ARCH=${CUDA_DOCKER_ARCH}
2323
# Enable CUDA
2424
ENV LLAMA_CUDA=1
2525

26-
RUN make
26+
RUN make -j$(nproc) main
2727

2828
FROM ${BASE_CUDA_RUN_CONTAINER} as runtime
2929

30+
RUN apt-get update && \
31+
apt-get install -y libgomp1
32+
3033
COPY --from=build /app/main /main
3134

3235
ENTRYPOINT [ "/main" ]

‎.devops/main-intel.Dockerfile

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,14 @@ ARG ONEAPI_VERSION=2024.0.1-devel-ubuntu22.04
22

33
FROM intel/oneapi-basekit:$ONEAPI_VERSION as build
44

5+
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 && \
6+
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 && \
7+
chmod 644 /usr/share/keyrings/intel-oneapi-archive-keyring.gpg && \
8+
rm /etc/apt/sources.list.d/intel-graphics.list && \
9+
wget -O- https://repositories.intel.com/graphics/intel-graphics.key | gpg --dearmor | tee /usr/share/keyrings/intel-graphics.gpg > /dev/null && \
10+
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 && \
11+
chmod 644 /usr/share/keyrings/intel-graphics.gpg
12+
513
ARG LLAMA_SYCL_F16=OFF
614
RUN apt-get update && \
715
apt-get install -y git

‎.devops/main-rocm.Dockerfile

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -40,6 +40,6 @@ ENV LLAMA_HIPBLAS=1
4040
ENV CC=/opt/rocm/llvm/bin/clang
4141
ENV CXX=/opt/rocm/llvm/bin/clang++
4242

43-
RUN make
43+
RUN make -j$(nproc) main
4444

4545
ENTRYPOINT [ "/app/main" ]

‎.devops/main-vulkan.Dockerfile

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ ARG UBUNTU_VERSION=jammy
33
FROM ubuntu:$UBUNTU_VERSION as build
44

55
# Install build tools
6-
RUN apt update && apt install -y git build-essential cmake wget
6+
RUN apt update && apt install -y git build-essential cmake wget libgomp1
77

88
# Install Vulkan SDK
99
RUN wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | apt-key add - && \

‎.devops/main.Dockerfile

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -9,10 +9,13 @@ WORKDIR /app
99

1010
COPY . .
1111

12-
RUN make
12+
RUN make -j$(nproc) main
1313

1414
FROM ubuntu:$UBUNTU_VERSION as runtime
1515

16+
RUN apt-get update && \
17+
apt-get install -y libgomp1
18+
1619
COPY --from=build /app/main /main
1720

1821
ENV LC_ALL=C.utf8

‎.devops/server-cuda.Dockerfile

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -25,12 +25,12 @@ ENV LLAMA_CUDA=1
2525
# Enable cURL
2626
ENV LLAMA_CURL=1
2727

28-
RUN make
28+
RUN make -j$(nproc) server
2929

3030
FROM ${BASE_CUDA_RUN_CONTAINER} as runtime
3131

3232
RUN apt-get update && \
33-
apt-get install -y libcurl4-openssl-dev
33+
apt-get install -y libcurl4-openssl-dev libgomp1
3434

3535
COPY --from=build /app/server /server
3636

‎.devops/server-intel.Dockerfile

Lines changed: 16 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,14 @@ ARG ONEAPI_VERSION=2024.0.1-devel-ubuntu22.04
22

33
FROM intel/oneapi-basekit:$ONEAPI_VERSION as build
44

5+
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 && \
6+
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 && \
7+
chmod 644 /usr/share/keyrings/intel-oneapi-archive-keyring.gpg && \
8+
rm /etc/apt/sources.list.d/intel-graphics.list && \
9+
wget -O- https://repositories.intel.com/graphics/intel-graphics.key | gpg --dearmor | tee /usr/share/keyrings/intel-graphics.gpg > /dev/null && \
10+
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 && \
11+
chmod 644 /usr/share/keyrings/intel-graphics.gpg
12+
513
ARG LLAMA_SYCL_F16=OFF
614
RUN apt-get update && \
715
apt-get install -y git libcurl4-openssl-dev
@@ -19,6 +27,14 @@ RUN if [ "${LLAMA_SYCL_F16}" = "ON" ]; then \
1927

2028
FROM intel/oneapi-basekit:$ONEAPI_VERSION as runtime
2129

30+
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 && \
31+
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 && \
32+
chmod 644 /usr/share/keyrings/intel-oneapi-archive-keyring.gpg && \
33+
rm /etc/apt/sources.list.d/intel-graphics.list && \
34+
wget -O- https://repositories.intel.com/graphics/intel-graphics.key | gpg --dearmor | tee /usr/share/keyrings/intel-graphics.gpg > /dev/null && \
35+
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 && \
36+
chmod 644 /usr/share/keyrings/intel-graphics.gpg
37+
2238
RUN apt-get update && \
2339
apt-get install -y libcurl4-openssl-dev
2440

‎.devops/server-rocm.Dockerfile

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -45,6 +45,6 @@ ENV LLAMA_CURL=1
4545
RUN apt-get update && \
4646
apt-get install -y libcurl4-openssl-dev
4747

48-
RUN make
48+
RUN make -j$(nproc)
4949

5050
ENTRYPOINT [ "/app/server" ]

‎.devops/server.Dockerfile

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -11,12 +11,12 @@ COPY . .
1111

1212
ENV LLAMA_CURL=1
1313

14-
RUN make
14+
RUN make -j$(nproc) server
1515

1616
FROM ubuntu:$UBUNTU_VERSION as runtime
1717

1818
RUN apt-get update && \
19-
apt-get install -y libcurl4-openssl-dev
19+
apt-get install -y libcurl4-openssl-dev libgomp1
2020

2121
COPY --from=build /app/server /server
2222

‎.devops/tools.sh

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,7 @@ arg1="$1"
88
shift
99

1010
if [[ "$arg1" == '--convert' || "$arg1" == '-c' ]]; then
11-
python3 ./convert.py "$@"
11+
python3 ./convert-hf-to-gguf.py "$@"
1212
elif [[ "$arg1" == '--quantize' || "$arg1" == '-q' ]]; then
1313
./quantize "$@"
1414
elif [[ "$arg1" == '--run' || "$arg1" == '-r' ]]; then

‎.github/ISSUE_TEMPLATE/01-bug-low.yml

Lines changed: 50 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,50 @@
1+
name: Low Severity Bugs
2+
description: Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
3+
title: "Bug: "
4+
labels: ["bug-unconfirmed", "low severity"]
5+
body:
6+
- type: markdown
7+
attributes:
8+
value: |
9+
Thanks for taking the time to fill out this bug report!
10+
Please include information about your system, the steps to reproduce the bug,
11+
and the version of llama.cpp that you are using.
12+
If possible, please provide a minimal code example that reproduces the bug.
13+
- type: textarea
14+
id: what-happened
15+
attributes:
16+
label: What happened?
17+
description: Also tell us, what did you expect to happen?
18+
placeholder: Tell us what you see!
19+
validations:
20+
required: true
21+
- type: textarea
22+
id: version
23+
attributes:
24+
label: Name and Version
25+
description: Which executable and which version of our software are you running? (use `--version` to get a version string)
26+
placeholder: |
27+
$./main --version
28+
version: 2999 (42b4109e)
29+
built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
30+
validations:
31+
required: true
32+
- type: dropdown
33+
id: operating-system
34+
attributes:
35+
label: What operating system are you seeing the problem on?
36+
multiple: true
37+
options:
38+
- Linux
39+
- Mac
40+
- Windows
41+
- BSD
42+
- Other? (Please let us know in description)
43+
validations:
44+
required: false
45+
- type: textarea
46+
id: logs
47+
attributes:
48+
label: Relevant log output
49+
description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
50+
render: shell

‎.github/ISSUE_TEMPLATE/02-bug-medium.yml

Lines changed: 50 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,50 @@
1+
name: Medium Severity Bug
2+
description: Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but generally still useable)
3+
title: "Bug: "
4+
labels: ["bug-unconfirmed", "medium severity"]
5+
body:
6+
- type: markdown
7+
attributes:
8+
value: |
9+
Thanks for taking the time to fill out this bug report!
10+
Please include information about your system, the steps to reproduce the bug,
11+
and the version of llama.cpp that you are using.
12+
If possible, please provide a minimal code example that reproduces the bug.
13+
- type: textarea
14+
id: what-happened
15+
attributes:
16+
label: What happened?
17+
description: Also tell us, what did you expect to happen?
18+
placeholder: Tell us what you see!
19+
validations:
20+
required: true
21+
- type: textarea
22+
id: version
23+
attributes:
24+
label: Name and Version
25+
description: Which executable and which version of our software are you running? (use `--version` to get a version string)
26+
placeholder: |
27+
$./main --version
28+
version: 2999 (42b4109e)
29+
built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
30+
validations:
31+
required: true
32+
- type: dropdown
33+
id: operating-system
34+
attributes:
35+
label: What operating system are you seeing the problem on?
36+
multiple: true
37+
options:
38+
- Linux
39+
- Mac
40+
- Windows
41+
- BSD
42+
- Other? (Please let us know in description)
43+
validations:
44+
required: false
45+
- type: textarea
46+
id: logs
47+
attributes:
48+
label: Relevant log output
49+
description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
50+
render: shell

‎.github/ISSUE_TEMPLATE/03-bug-high.yml

Lines changed: 50 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,50 @@
1+
name: High Severity Bug
2+
description: Used to report high severity bugs in llama.cpp (e.g. Malfunctioning features hindering important common workflow)
3+
title: "Bug: "
4+
labels: ["bug-unconfirmed", "high severity"]
5+
body:
6+
- type: markdown
7+
attributes:
8+
value: |
9+
Thanks for taking the time to fill out this bug report!
10+
Please include information about your system, the steps to reproduce the bug,
11+
and the version of llama.cpp that you are using.
12+
If possible, please provide a minimal code example that reproduces the bug.
13+
- type: textarea
14+
id: what-happened
15+
attributes:
16+
label: What happened?
17+
description: Also tell us, what did you expect to happen?
18+
placeholder: Tell us what you see!
19+
validations:
20+
required: true
21+
- type: textarea
22+
id: version
23+
attributes:
24+
label: Name and Version
25+
description: Which executable and which version of our software are you running? (use `--version` to get a version string)
26+
placeholder: |
27+
$./main --version
28+
version: 2999 (42b4109e)
29+
built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
30+
validations:
31+
required: true
32+
- type: dropdown
33+
id: operating-system
34+
attributes:
35+
label: What operating system are you seeing the problem on?
36+
multiple: true
37+
options:
38+
- Linux
39+
- Mac
40+
- Windows
41+
- BSD
42+
- Other? (Please let us know in description)
43+
validations:
44+
required: false
45+
- type: textarea
46+
id: logs
47+
attributes:
48+
label: Relevant log output
49+
description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
50+
render: shell

‎.github/ISSUE_TEMPLATE/04-bug-critical.yml

Lines changed: 50 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,50 @@
1+
name: Critical Severity Bug
2+
description: Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
3+
title: "Bug: "
4+
labels: ["bug-unconfirmed", "critical severity"]
5+
body:
6+
- type: markdown
7+
attributes:
8+
value: |
9+
Thanks for taking the time to fill out this bug report!
10+
Please include information about your system, the steps to reproduce the bug,
11+
and the version of llama.cpp that you are using.
12+
If possible, please provide a minimal code example that reproduces the bug.
13+
- type: textarea
14+
id: what-happened
15+
attributes:
16+
label: What happened?
17+
description: Also tell us, what did you expect to happen?
18+
placeholder: Tell us what you see!
19+
validations:
20+
required: true
21+
- type: textarea
22+
id: version
23+
attributes:
24+
label: Name and Version
25+
description: Which executable and which version of our software are you running? (use `--version` to get a version string)
26+
placeholder: |
27+
$./main --version
28+
version: 2999 (42b4109e)
29+
built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
30+
validations:
31+
required: true
32+
- type: dropdown
33+
id: operating-system
34+
attributes:
35+
label: What operating system are you seeing the problem on?
36+
multiple: true
37+
options:
38+
- Linux
39+
- Mac
40+
- Windows
41+
- BSD
42+
- Other? (Please let us know in description)
43+
validations:
44+
required: false
45+
- type: textarea
46+
id: logs
47+
attributes:
48+
label: Relevant log output
49+
description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
50+
render: shell

0 commit comments

Comments
 (0)