Skip to content

Commit ad4f275

Browse files
committed
feat(ci): add CUDA 11.8 wheel builds
1 parent c7af423 commit ad4f275

3 files changed

Lines changed: 4 additions & 2 deletions

File tree

‎.github/workflows/build-wheels-cuda.yaml‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -24,7 +24,7 @@ jobs:
2424
# wheel.py-api = "py3" makes the CUDA wheel interpreter-agnostic,
2525
# so one builder per toolkit version is sufficient.
2626
'pyver' = @("3.9")
27-
'cuda' = @("12.1.1", "12.2.2", "12.3.2", "12.4.1", "12.5.1")
27+
'cuda' = @("11.8.0", "12.1.1", "12.2.2", "12.3.2", "12.4.1", "12.5.1")
2828
'releasetag' = @("basic")
2929
'exclude' = @(
3030
@{ 'os' = 'windows-2022'; 'cuda' = '12.1.1' },

‎CHANGELOG.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -7,6 +7,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
77

88
## [Unreleased]
99

10+
- feat(ci): add CUDA 11.8 wheel builds by @abetlen in #2238
1011
- fix(ci): add Pascal compute capability targets to CUDA wheel builds by @abetlen in #2237
1112

1213
## [0.3.24]

‎README.md‎

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -125,7 +125,7 @@ CMAKE_ARGS="-DGGML_CUDA=on" pip install llama-cpp-python
125125

126126
It is also possible to install a pre-built wheel with CUDA support. As long as your system meets some requirements:
127127

128-
- CUDA Version is 12.1, 12.2, 12.3, 12.4 or 12.5
128+
- CUDA Version is 11.8, 12.1, 12.2, 12.3, 12.4 or 12.5
129129
- NVIDIA GPU compute capability is 6.0 or newer
130130
- Python Version is 3.10, 3.11 or 3.12
131131

@@ -135,6 +135,7 @@ pip install llama-cpp-python \
135135
```
136136

137137
Where `<cuda-version>` is one of the following:
138+
- `cu118`: CUDA 11.8
138139
- `cu121`: CUDA 12.1
139140
- `cu122`: CUDA 12.2
140141
- `cu123`: CUDA 12.3

0 commit comments

Comments
 (0)