Atinoda
e6f0ec9837
Bump CUDA version to 12.1
...
Fixes #31
11 months ago
Atinoda
0575195a24
Pin torch to CUDA 11.8
12 months ago
Atinoda
123618d6bf
Remove hotfix for ExLlamaV2
...
Issue is resolved upstream
1 year ago
Atinoda
e704efd2fa
Hotfix for ExLlamaV2
...
See:
https://github.com/oobabooga/text-generation-webui/issues/4002
and
ec5164b8a8
?diff=split
1 year ago
Atinoda
faab710cbc
Add Exllamav2 to base image
1 year ago
Atinoda
43392402e0
Deprecate `llama-cublas` variant
...
`default` already includes CUDA GPU offloading for llama
1 year ago
Atinoda
f85bf702ea
Implement versioned builds
...
- Introduce new build arg `VERSION_TAG`
- Update version freshness checking
- Rename docker-compose build example file
1 year ago
Atinoda
79c7cf645e
Fix `CMD` for `llama-cpu` variant
1 year ago
Atinoda
00340c0504
Create `llama-cpu` variant for systems without GPU
...
Fixes #16
1 year ago
Atinoda
4c24344796
Remove ExLlama manual installation (no longer required)
1 year ago
Atinoda
84c1bbe883
Integrate `llama-cublas` into base image
...
- Update README.md with deprecation warnings and improved descriptions.
- Fix the build error in the latest `llama-cpp-python` version by removing CMAKE directives.
1 year ago
Atinoda
ff496b6929
Integrate ExLlama in base image
...
Closes #6
1 year ago
Atinoda
19f9c1b1ac
Implement persistent extensions with optional runtime build
...
- Extensions are now explicitly copied from source to named volume
- Optional rebuild at runtime allows for extensions not present during build
- Closes #3
1 year ago
Atinoda
7caaaa4a7c
Update to upstream changes
...
- AutoGPTQ manual installation removed (it is included in requirements)
- Softprompt config removed
- Build date print-out added to `docker-entrypoint.sh`
- `README.md` updated
1 year ago
Atinoda
a0137d40b8
Refactor to pull Docker hub images
...
Also fixes `triton` dependency conflict
1 year ago
Atinoda
b29d617880
Fix `cuda` variant dependency conflict
...
This variant will be pruned at a later date if the upstream author does not continue development on the branch.
1 year ago
Atinoda
a75df0d7ae
Integrate AutoGPTQ into base image
1 year ago
Atinoda
14a3bd3138
Implement `monkey-patch` variant
1 year ago
Atinoda
dd8dab6fb9
Implement llama-cpp with CUBLAS
...
Also switch to devel image for deployment - it will be more flexible for variant builds.
1 year ago
Atinoda
bd884491e4
Initial commit
1 year ago