Skip to content

Releases: ai-dock/llama.cpp-cuda

llama.cpp b8389 with CUDA

17 Mar 03:28
@github-actions github-actions
b8389
9d1bd0d
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
llama.cpp b8389 with CUDA Latest
Latest

llama.cpp b8389 with CUDA Support

Pre-built binaries of llama.cpp with CUDA support for multiple CUDA versions.

Source: https://github.com/ggml-org/llama.cpp/releases/tag/b8389
Commit: 2e4a6edd4ac6ebb2459fca373249298291acfc5e

CUDA Versions

  • CUDA 12.8 - Architectures: 7.5, 8.0, 8.6, 8.9, 9.0, 10.0, 12.0

Architecture Reference

  • 7.5: Tesla T4, RTX 20xx series, Quadro RTX
  • 8.0: A100
  • 8.6: RTX 3000 series
  • 8.9: RTX 4000 series, L4, L40
  • 9.0: H100, H200
  • 10.0: B200
  • 12.0: RTX Pro series, RTX 50xx

Usage

Download the appropriate tarball for your CUDA version and extract:

tar -xzf llama.cpp-b8389-cuda-12.8.tar.gz
./llama-cli --help
Assets 3
Loading

llama.cpp b8368 with CUDA

16 Mar 03:45
@github-actions github-actions
b8368
9d1bd0d
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
llama.cpp b8368 with CUDA

llama.cpp b8368 with CUDA Support

Pre-built binaries of llama.cpp with CUDA support for multiple CUDA versions.

Source: https://github.com/ggml-org/llama.cpp/releases/tag/b8368
Commit: 9e2e2198b006b5bcb81846a43b868528ea79a483

CUDA Versions

  • CUDA 12.8 - Architectures: 7.5, 8.0, 8.6, 8.9, 9.0, 10.0, 12.0

Architecture Reference

  • 7.5: Tesla T4, RTX 20xx series, Quadro RTX
  • 8.0: A100
  • 8.6: RTX 3000 series
  • 8.9: RTX 4000 series, L4, L40
  • 9.0: H100, H200
  • 10.0: B200
  • 12.0: RTX Pro series, RTX 50xx

Usage

Download the appropriate tarball for your CUDA version and extract:

tar -xzf llama.cpp-b8368-cuda-12.8.tar.gz
./llama-cli --help
Loading

llama.cpp b8352 with CUDA

15 Mar 03:43
@github-actions github-actions
b8352
9d1bd0d
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
llama.cpp b8352 with CUDA

llama.cpp b8352 with CUDA Support

Pre-built binaries of llama.cpp with CUDA support for multiple CUDA versions.

Source: https://github.com/ggml-org/llama.cpp/releases/tag/b8352
Commit: d23355afc319f598d0e588a2d16a4da82e14ff41

CUDA Versions

  • CUDA 12.8 - Architectures: 7.5, 8.0, 8.6, 8.9, 9.0, 10.0, 12.0

Architecture Reference

  • 7.5: Tesla T4, RTX 20xx series, Quadro RTX
  • 8.0: A100
  • 8.6: RTX 3000 series
  • 8.9: RTX 4000 series, L4, L40
  • 9.0: H100, H200
  • 10.0: B200
  • 12.0: RTX Pro series, RTX 50xx

Usage

Download the appropriate tarball for your CUDA version and extract:

tar -xzf llama.cpp-b8352-cuda-12.8.tar.gz
./llama-cli --help
Loading

llama.cpp b8298 with CUDA

13 Mar 03:25
@github-actions github-actions
b8298
9d1bd0d
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
llama.cpp b8298 with CUDA

llama.cpp b8298 with CUDA Support

Pre-built binaries of llama.cpp with CUDA support for multiple CUDA versions.

Source: https://github.com/ggml-org/llama.cpp/releases/tag/b8298
Commit: f90bd1dd84b59d75ab7d442228b67ec9a797577c

CUDA Versions

  • CUDA 12.8 - Architectures: 7.5, 8.0, 8.6, 8.9, 9.0, 10.0, 12.0

Architecture Reference

  • 7.5: Tesla T4, RTX 20xx series, Quadro RTX
  • 8.0: A100
  • 8.6: RTX 3000 series
  • 8.9: RTX 4000 series, L4, L40
  • 9.0: H100, H200
  • 10.0: B200
  • 12.0: RTX Pro series, RTX 50xx

Usage

Download the appropriate tarball for your CUDA version and extract:

tar -xzf llama.cpp-b8298-cuda-12.8.tar.gz
./llama-cli --help
Loading

llama.cpp b8280 with CUDA

12 Mar 03:24
@github-actions github-actions
b8280
9d1bd0d
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
llama.cpp b8280 with CUDA

llama.cpp b8280 with CUDA Support

Pre-built binaries of llama.cpp with CUDA support for multiple CUDA versions.

Source: https://github.com/ggml-org/llama.cpp/releases/tag/b8280
Commit: b2e1427c9b78a937ff2907ae3f2d998512f29c02

CUDA Versions

  • CUDA 12.8 - Architectures: 7.5, 8.0, 8.6, 8.9, 9.0, 10.0, 12.0

Architecture Reference

  • 7.5: Tesla T4, RTX 20xx series, Quadro RTX
  • 8.0: A100
  • 8.6: RTX 3000 series
  • 8.9: RTX 4000 series, L4, L40
  • 9.0: H100, H200
  • 10.0: B200
  • 12.0: RTX Pro series, RTX 50xx

Usage

Download the appropriate tarball for your CUDA version and extract:

tar -xzf llama.cpp-b8280-cuda-12.8.tar.gz
./llama-cli --help
Loading

llama.cpp b8263 with CUDA

11 Mar 03:23
@github-actions github-actions
b8263
9d1bd0d
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
llama.cpp b8263 with CUDA

llama.cpp b8263 with CUDA Support

Pre-built binaries of llama.cpp with CUDA support for multiple CUDA versions.

Source: https://github.com/ggml-org/llama.cpp/releases/tag/b8263
Commit: 59db9a357d9a247009c70fda34050661b17a1a5c

CUDA Versions

  • CUDA 12.8 - Architectures: 7.5, 8.0, 8.6, 8.9, 9.0, 10.0, 12.0

Architecture Reference

  • 7.5: Tesla T4, RTX 20xx series, Quadro RTX
  • 8.0: A100
  • 8.6: RTX 3000 series
  • 8.9: RTX 4000 series, L4, L40
  • 9.0: H100, H200
  • 10.0: B200
  • 12.0: RTX Pro series, RTX 50xx

Usage

Download the appropriate tarball for your CUDA version and extract:

tar -xzf llama.cpp-b8263-cuda-12.8.tar.gz
./llama-cli --help
Loading

llama.cpp b8252 with CUDA

10 Mar 03:22
@github-actions github-actions
b8252
9d1bd0d
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
llama.cpp b8252 with CUDA

llama.cpp b8252 with CUDA Support

Pre-built binaries of llama.cpp with CUDA support for multiple CUDA versions.

Source: https://github.com/ggml-org/llama.cpp/releases/tag/b8252
Commit: b518195101fda6e3e636d997d487c83a629a0089

CUDA Versions

  • CUDA 12.8 - Architectures: 7.5, 8.0, 8.6, 8.9, 9.0, 10.0, 12.0

Architecture Reference

  • 7.5: Tesla T4, RTX 20xx series, Quadro RTX
  • 8.0: A100
  • 8.6: RTX 3000 series
  • 8.9: RTX 4000 series, L4, L40
  • 9.0: H100, H200
  • 10.0: B200
  • 12.0: RTX Pro series, RTX 50xx

Usage

Download the appropriate tarball for your CUDA version and extract:

tar -xzf llama.cpp-b8252-cuda-12.8.tar.gz
./llama-cli --help
Loading

llama.cpp b8245 with CUDA

09 Mar 03:32
@github-actions github-actions
b8245
9d1bd0d
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
llama.cpp b8245 with CUDA

llama.cpp b8245 with CUDA Support

Pre-built binaries of llama.cpp with CUDA support for multiple CUDA versions.

Source: https://github.com/ggml-org/llama.cpp/releases/tag/b8245
Commit: d417bc43dd29eab006a0da73afc7d610c9ebae7d

CUDA Versions

  • CUDA 12.8 - Architectures: 7.5, 8.0, 8.6, 8.9, 9.0, 10.0, 12.0

Architecture Reference

  • 7.5: Tesla T4, RTX 20xx series, Quadro RTX
  • 8.0: A100
  • 8.6: RTX 3000 series
  • 8.9: RTX 4000 series, L4, L40
  • 9.0: H100, H200
  • 10.0: B200
  • 12.0: RTX Pro series, RTX 50xx

Usage

Download the appropriate tarball for your CUDA version and extract:

tar -xzf llama.cpp-b8245-cuda-12.8.tar.gz
./llama-cli --help
Loading

llama.cpp b8233 with CUDA

08 Mar 03:28
@github-actions github-actions
b8233
9d1bd0d
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
llama.cpp b8233 with CUDA

llama.cpp b8233 with CUDA Support

Pre-built binaries of llama.cpp with CUDA support for multiple CUDA versions.

Source: https://github.com/ggml-org/llama.cpp/releases/tag/b8233
Commit: c5a778891ba0ddbd4cbb507c823f970595b1adc2

CUDA Versions

  • CUDA 12.8 - Architectures: 7.5, 8.0, 8.6, 8.9, 9.0, 10.0, 12.0

Architecture Reference

  • 7.5: Tesla T4, RTX 20xx series, Quadro RTX
  • 8.0: A100
  • 8.6: RTX 3000 series
  • 8.9: RTX 4000 series, L4, L40
  • 9.0: H100, H200
  • 10.0: B200
  • 12.0: RTX Pro series, RTX 50xx

Usage

Download the appropriate tarball for your CUDA version and extract:

tar -xzf llama.cpp-b8233-cuda-12.8.tar.gz
./llama-cli --help
Loading

llama.cpp b8219 with CUDA

07 Mar 03:09
@github-actions github-actions
b8219
9d1bd0d
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
llama.cpp b8219 with CUDA

llama.cpp b8219 with CUDA Support

Pre-built binaries of llama.cpp with CUDA support for multiple CUDA versions.

Source: https://github.com/ggml-org/llama.cpp/releases/tag/b8219
Commit: 388baabc06be4cbcb64b546c4b67a1aa2f64858b

CUDA Versions

  • CUDA 12.8 - Architectures: 7.5, 8.0, 8.6, 8.9, 9.0, 10.0, 12.0

Architecture Reference

  • 7.5: Tesla T4, RTX 20xx series, Quadro RTX
  • 8.0: A100
  • 8.6: RTX 3000 series
  • 8.9: RTX 4000 series, L4, L40
  • 9.0: H100, H200
  • 10.0: B200
  • 12.0: RTX Pro series, RTX 50xx

Usage

Download the appropriate tarball for your CUDA version and extract:

tar -xzf llama.cpp-b8219-cuda-12.8.tar.gz
./llama-cli --help
Loading