Skip to content

Commit d7cc6bc

Browse files
mofosynemofosyne
authored
Merge branch 'master' into sl/blas-backend
2 parents 515e2a9 + 5dcdf94 commit d7cc6bc

File tree

189 files changed

+34704
-19925
lines changed

Some content is hidden

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

189 files changed

+34704
-19925
lines changed

‎.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/nix/package.nix‎

Lines changed: 8 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -214,7 +214,6 @@ effectiveStdenv.mkDerivation (
214214
(cmakeBool "LLAMA_CUDA" useCuda)
215215
(cmakeBool "LLAMA_HIPBLAS" useRocm)
216216
(cmakeBool "LLAMA_METAL" useMetalKit)
217-
(cmakeBool "LLAMA_MPI" useMpi)
218217
(cmakeBool "LLAMA_VULKAN" useVulkan)
219218
(cmakeBool "LLAMA_STATIC" enableStatic)
220219
]
@@ -227,20 +226,20 @@ effectiveStdenv.mkDerivation (
227226
)
228227
]
229228
++ optionals useRocm [
230-
(cmakeFeature "CMAKE_C_COMPILER" "hipcc")
231-
(cmakeFeature "CMAKE_CXX_COMPILER" "hipcc")
232-
233-
# Build all targets supported by rocBLAS. When updating search for TARGET_LIST_ROCM
234-
# in https://github.com/ROCmSoftwarePlatform/rocBLAS/blob/develop/CMakeLists.txt
235-
# and select the line that matches the current nixpkgs version of rocBLAS.
236-
# Should likely use `rocmPackages.clr.gpuTargets`.
237-
"-DAMDGPU_TARGETS=gfx803;gfx900;gfx906:xnack-;gfx908:xnack-;gfx90a:xnack+;gfx90a:xnack-;gfx940;gfx941;gfx942;gfx1010;gfx1012;gfx1030;gfx1100;gfx1101;gfx1102"
229+
(cmakeFeature "CMAKE_HIP_COMPILER" "${rocmPackages.llvm.clang}/bin/clang")
230+
(cmakeFeature "CMAKE_HIP_ARCHITECTURES" (builtins.concatStringsSep ";" rocmPackages.clr.gpuTargets))
238231
]
239232
++ optionals useMetalKit [
240233
(lib.cmakeFeature "CMAKE_C_FLAGS" "-D__ARM_FEATURE_DOTPROD=1")
241234
(cmakeBool "LLAMA_METAL_EMBED_LIBRARY" (!precompileMetalShaders))
242235
];
243236

237+
# Environment variables needed for ROCm
238+
env = optionals useRocm {
239+
ROCM_PATH = "${rocmPackages.clr}";
240+
HIP_DEVICE_LIB_PATH = "${rocmPackages.rocm-device-libs}/amdgcn/bitcode";
241+
};
242+
244243
# TODO(SomeoneSerge): It's better to add proper install targets at the CMake level,
245244
# if they haven't been added yet.
246245
postInstall = ''

‎.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/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

‎.github/ISSUE_TEMPLATE/05-enhancement.yml‎

Lines changed: 51 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,51 @@
1+
name: Enhancement
2+
description: Used to request enhancements for llama.cpp
3+
title: "Feature Request: "
4+
labels: ["enhancement"]
5+
body:
6+
- type: markdown
7+
attributes:
8+
value: |
9+
[Please post your idea first in Discussion if there is not yet a consensus for this enhancement request. This will help to keep this issue tracker focused on enhancements that the community has agreed needs to be implemented.](https://github.com/ggerganov/llama.cpp/discussions/categories/ideas)
10+
11+
- type: checkboxes
12+
id: prerequisites
13+
attributes:
14+
label: Prerequisites
15+
description: Please confirm the following before submitting your enhancement request.
16+
options:
17+
- label: I am running the latest code. Mention the version if possible as well.
18+
required: true
19+
- label: I carefully followed the [README.md](https://github.com/ggerganov/llama.cpp/blob/master/README.md).
20+
required: true
21+
- label: I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
22+
required: true
23+
- label: I reviewed the [Discussions](https://github.com/ggerganov/llama.cpp/discussions), and have a new and useful enhancement to share.
24+
required: true
25+
26+
- type: textarea
27+
id: feature-description
28+
attributes:
29+
label: Feature Description
30+
description: Please provide a detailed written description of what you were trying to do, and what you expected `llama.cpp` to do as an enhancement.
31+
placeholder: Detailed description of the enhancement
32+
validations:
33+
required: true
34+
35+
- type: textarea
36+
id: motivation
37+
attributes:
38+
label: Motivation
39+
description: Please provide a detailed written description of reasons why this feature is necessary and how it is useful to `llama.cpp` users.
40+
placeholder: Explanation of why this feature is needed and its benefits
41+
validations:
42+
required: true
43+
44+
- type: textarea
45+
id: possible-implementation
46+
attributes:
47+
label: Possible Implementation
48+
description: If you have an idea as to how it can be implemented, please write a detailed description. Feel free to give links to external sources or share visuals that might be helpful to understand the details better.
49+
placeholder: Detailed description of potential implementation
50+
validations:
51+
required: false

‎.github/ISSUE_TEMPLATE/06-research.yml‎

Lines changed: 52 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,52 @@
1+
name: Research
2+
description: Track new technical research area
3+
title: "Research: "
4+
labels: ["research 🔬"]
5+
body:
6+
- type: markdown
7+
attributes:
8+
value: |
9+
Don't forget to check for any [duplicate research issue tickets](https://github.com/ggerganov/llama.cpp/issues?q=is%3Aopen+is%3Aissue+label%3A%22research+%F0%9F%94%AC%22)
10+
11+
- type: checkboxes
12+
id: research-stage
13+
attributes:
14+
label: Research Stage
15+
description: Track general state of this research ticket
16+
options:
17+
- label: Background Research (Let's try to avoid reinventing the wheel)
18+
- label: Hypothesis Formed (How do you think this will work and it's effect?)
19+
- label: Strategy / Implementation Forming
20+
- label: Analysis of results
21+
- label: Debrief / Documentation (So people in the future can learn from us)
22+
23+
- type: textarea
24+
id: background
25+
attributes:
26+
label: Previous existing literature and research
27+
description: Whats the current state of the art and whats the motivation for this research?
28+
29+
- type: textarea
30+
id: hypothesis
31+
attributes:
32+
label: Hypothesis
33+
description: How do you think this will work and it's effect?
34+
35+
- type: textarea
36+
id: implementation
37+
attributes:
38+
label: Implementation
39+
description: Got an approach? e.g. a PR ready to go?
40+
41+
- type: textarea
42+
id: analysis
43+
attributes:
44+
label: Analysis
45+
description: How does the proposed implementation behave?
46+
47+
- type: textarea
48+
id: logs
49+
attributes:
50+
label: Relevant log output
51+
description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
52+
render: shell

0 commit comments

Comments
 (0)