Atinoda
e704efd2fa
Hotfix for ExLlamaV2
...
See:
https://github.com/oobabooga/text-generation-webui/issues/4002
and
ec5164b8a8
2023-09-21 12:08:39 +01:00
Atinoda
faab710cbc
Add Exllamav2 to base image
2023-09-18 21:15:05 +01:00
Atinoda
43392402e0
Deprecate llama-cublas variant
...
`default` already includes CUDA GPU offloading for llama
2023-08-28 15:28:17 +01:00
Atinoda
f85bf702ea
Implement versioned builds
...
- Introduce new build arg `VERSION_TAG`
- Update version freshness checking
- Rename docker-compose build example file
2023-08-28 15:21:03 +01:00
Atinoda
79c7cf645e
Fix CMD for llama-cpu variant
2023-08-04 14:39:41 +01:00
Atinoda
00340c0504
Create llama-cpu variant for systems without GPU
...
Fixes #16
2023-08-04 14:26:05 +01:00
Atinoda
4c24344796
Remove ExLlama manual installation (no longer required)
2023-06-27 19:44:08 +01:00
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.
2023-06-23 15:00:43 +01:00
Atinoda
ff496b6929
Integrate ExLlama in base image
...
Closes #6
2023-06-19 23:13:25 +01:00
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
2023-06-13 09:54:12 +01:00
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
2023-06-07 10:34:44 +01:00
Atinoda
a0137d40b8
Refactor to pull Docker hub images
...
Also fixes `triton` dependency conflict
2023-06-03 15:40:35 +01:00
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.
2023-06-03 11:45:26 +01:00
Atinoda
a75df0d7ae
Integrate AutoGPTQ into base image
2023-05-29 22:52:13 +01:00
Atinoda
14a3bd3138
Implement monkey-patch variant
2023-05-25 16:19:03 +01:00
Atinoda
dd8dab6fb9
Implement llama-cpp with CUBLAS
...
Also switch to devel image for deployment - it will be more flexible for variant builds.
2023-05-21 22:41:06 +01:00
Atinoda
bd884491e4
Initial commit
2023-05-17 20:34:52 +01:00
