1fdefb70de
Remove deprecated information
2 months ago
2f8b2fe4bb
Update deployment parameters
...
- Remove compose `version`
- Update folder structure with
- `cache`
- `instruction-templates`
- Add examples for ROCM/AMD deployment
- Add examples for custom embedding configurations
2 months ago
afeeb9e8ae
Fix launch arg array handling
3 months ago
6726a71bf6
Bump torch versions
...
Closes #44
3 months ago
994e701bf2
Rephrase ROCM and Arc variants support
4 months ago
6f2d496213
Delete `arc` and `rocm` nightlies
4 months ago
02ebf86b5f
Add ROCM test results to README.md
4 months ago
083d958ced
Create LICENSE
...
AGPL-3.0 license, matching the containerised project.
4 months ago
58392b249b
Update docs for refactored variants
4 months ago
d21346e3f4
Nightly workflows refactor ( #39 )
...
* Create default-nightly.yml
* Nightly variants
* Schedule nightly builds
* Disable arc nightly, More space required on builder
* Disable rocm nightly, More disk space required on builder
4 months ago
f971ca054d
Remove `unstable``tags from rocm and arc
4 months ago
76742f1fbd
Disable nightly builds
4 months ago
2a1dbbf43f
Update docs
4 months ago
0b6b7bc523
Update compose
4 months ago
b38cb4c9f9
Refactor Dockerfile and variants
4 months ago
e6f0ec9837
Bump CUDA version to 12.1
...
Fixes #31
8 months ago
d4b58daffe
Separate nightly builds
8 months ago
89aa0183ab
Improve documentation
...
- Add Quick-Start section
- Expand Usage description
- Signpost Kubernetes issue
- Deprecate `monkey-patch`
8 months ago
0575195a24
Pin torch to CUDA 11.8
8 months ago
123618d6bf
Remove hotfix for ExLlamaV2
...
Issue is resolved upstream
9 months ago
e704efd2fa
Hotfix for ExLlamaV2
...
See:
https://github.com/oobabooga/text-generation-webui/issues/4002
and
ec5164b8a8
9 months ago
13c7bad5cd
Update README.md
9 months ago
8f7d865b5e
README.md spelling ( #24 )
9 months ago
faab710cbc
Add Exllamav2 to base image
9 months ago
e1d999f0b0
Document dated milestone pseudo-version releases
9 months ago
5ff0a9571c
Delete docker-nightly.yml
10 months ago
ffd25bc4e1
Update README.md about versions and nightlies
10 months ago
65897fd7c1
Implement nightly builds of all variants
10 months ago
43392402e0
Deprecate `llama-cublas` variant
...
`default` already includes CUDA GPU offloading for llama
10 months ago
f85bf702ea
Implement versioned builds
...
- Introduce new build arg `VERSION_TAG`
- Update version freshness checking
- Rename docker-compose build example file
10 months ago
79c7cf645e
Fix `CMD` for `llama-cpu` variant
11 months ago
00340c0504
Create `llama-cpu` variant for systems without GPU
...
Fixes #16
11 months ago
6562cf0e16
Update config directories and compose example
...
Add `characters` directory to config
Remove softprompts from compose
11 months ago
b6b1ca1391
Implement per-extension initialisation
...
(Plansee)
11 months ago
4c24344796
Remove ExLlama manual installation (no longer required)
12 months ago
ef85657f3c
Implement Nightly builds as Github workflow ( #10 )
12 months ago
5b6477ddf3
Move nightly builds to dedicated branch
12 months ago
b9d7caffdf
Update docker-nightly.yml
12 months ago
f4638e1bd2
Create docker-nightly.yml
12 months ago
d8fcbd7ca3
Fix example standalone run commands
...
Credit to @sdizen in #7 connection refused issue - thanks for sharing the fix!
1 year ago
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
ff496b6929
Integrate ExLlama in base image
...
Closes #6
1 year ago
ee3f779157
Update README.md
1 year ago
56f068d4e8
Disable extensions folder mapping by default
1 year ago
068bea0948
Minor update README.me
1 year ago
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
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
524dad64c9
Fix `api` set up hint in README.md
1 year ago
a0137d40b8
Refactor to pull Docker hub images
...
Also fixes `triton` dependency conflict
1 year ago
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
Benjamin McLean