35 Commits (5ff0a9571c7caa71363151652efdf6632be0a600)
 

Author SHA1 Message Date
Atinoda 5ff0a9571c Delete docker-nightly.yml 10 months ago
Atinoda ffd25bc4e1 Update README.md about versions and nightlies 10 months ago
Atinoda 65897fd7c1 Implement nightly builds of all variants 10 months ago
Atinoda 43392402e0 Deprecate `llama-cublas` variant
`default` already includes CUDA GPU offloading for llama
10 months ago
Atinoda f85bf702ea Implement versioned builds
- Introduce new build arg `VERSION_TAG`
- Update version freshness checking
- Rename docker-compose build example file
10 months ago
Atinoda 79c7cf645e Fix `CMD` for `llama-cpu` variant 11 months ago
Atinoda 00340c0504 Create `llama-cpu` variant for systems without GPU
Fixes #16
11 months ago
Atinoda 6562cf0e16 Update config directories and compose example
Add `characters` directory to config
Remove softprompts from compose
11 months ago
Atinoda b6b1ca1391 Implement per-extension initialisation
(Plansee)
12 months ago
Atinoda 4c24344796 Remove ExLlama manual installation (no longer required) 1 year ago
Atinoda ef85657f3c
Implement Nightly builds as Github workflow (#10) 1 year ago
Atinoda 5b6477ddf3 Move nightly builds to dedicated branch 1 year ago
Atinoda b9d7caffdf
Update docker-nightly.yml 1 year ago
Atinoda f4638e1bd2
Create docker-nightly.yml 1 year ago
Atinoda d8fcbd7ca3
Fix example standalone run commands
Credit to @sdizen in #7 connection refused issue - thanks for sharing the fix!
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 ee3f779157
Update README.md 1 year ago
Atinoda 56f068d4e8 Disable extensions folder mapping by default 1 year ago
Atinoda 068bea0948 Minor update README.me 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 524dad64c9 Fix `api` set up hint in README.md 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 1f409aefcd Update README.md
Shoutout to PanQiWei.
1 year ago
Atinoda eafec5449a Update README.md 1 year ago
Atinoda a75df0d7ae Integrate AutoGPTQ into base image 1 year ago
Atinoda 19133da4a7 Add disclaimer 1 year ago
Atinoda f00296f970
PR: Instruct git to preserve .sh line endings
Instruct git to preserve .sh line endings
1 year ago
Atinoda e048102bfd Instruct git to preserve .sh line endings 1 year ago
Atinoda 14a3bd3138 Implement `monkey-patch` variant 1 year ago
Atinoda 1cfe526bb9 Improve config directory handling 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