ef483564fe
feat: integrate caddy, re-org paths ( #49 )
...
* integrate caddy
* address comments
2023-04-06 17:02:10 +08:00
93e4f5b3ca
refactor: default docker-compose w/ python backend
2023-04-06 00:50:24 +08:00
c46142385b
fix: properly set /data ownership
2023-04-05 23:13:34 +08:00
db77d7f267
feat: support single container ( #46 )
...
* docs: update readme
* fix: do not exclude peft
* Free disk space before docker building
* fix: fix docker-compose
* fix: dockercompose user to 1000
* fix dockerfile
* fix: cachedir ownership
2023-04-05 20:19:43 +08:00
1c61ef3944
feat: integrate projects / dataset information in admin. ( #38 )
...
* feat: add projects page in admin
* feat: integrate update_dataset job
* feat: display dataset info in projects
2023-04-03 13:04:04 +08:00
0a66a9d498
feat: support MODEL_REPLICA to control number of model instances in triton
2023-04-02 13:19:09 +08:00
477ef83319
Update startup_periord to 1200s as a HF model download might take time
2023-03-29 16:45:46 +08:00
20801bbe8c
Cleanup environment variable ( #30 )
...
* Remove EVENTS_LOG_DIR
* Rename supervisord.sh -> tabby.sh
2023-03-29 16:33:00 +08:00
bf7d149a27
Add supervisord to support a single docker run deployment ( #29 )
...
* Add suppervisord in dockerfile
* Create supervisord
* Update README.md
* Update README.md
2023-03-29 12:57:03 +08:00
d966f05abd
Add Completion Events & Acceptance Rate in metrics panel. ( #26 )
...
* Add duckdb
* Add basic Metrics w/duckdb
2023-03-28 20:12:03 +08:00
2f8714e6fe
Add vector logging for tabby-server events. ( #25 )
...
* Switch to dagu for init job
* Add processed logging
2023-03-28 16:32:35 +08:00
c990ba843f
Extract environment variable
2023-03-27 13:42:06 +08:00
9739683fba
Switch default deploy model ( #18 )
2023-03-27 01:10:15 +08:00
1c3ec20f93
Prepare public release with a minimal deployment setup ( #16 )
...
* Move deployment to deployment-next
* Add deployment setup
* Update deployment-next
* Remove vector label
* update README.md
2023-03-26 22:44:15 +08:00
e6bf16711f
Fix misc mistakes ( #13 )
...
* Fix misc
* Fix docker-compose
2023-03-25 21:37:38 +08:00
b622bd6762
use TabbyML/NeoX-70M for minimal e2e deployment ( #10 )
...
* use TabbyML/NeoX-70M for minimal e2e deployment
* Use python3 of triton image
2023-03-25 17:39:40 +08:00
8144e4f83a
Add tabby.tools.repository.updater for easier git repository synchronization. ( #9 )
...
* Move dags to tabby.tasks
* Add repository syncer
* Follow redirect for curl
2023-03-25 14:44:46 +08:00
8cf533016a
Move python code under tabby/ ( #8 )
...
* Add tabby config file
* Rename train.yaml to trainer.yaml
* Change server to relative import
* Move source files into tabby
* Rename conf
2023-03-25 12:20:29 +08:00
1038bb39a1
Add dagu for data processing job orchestration ( #7 )
...
* Install dagu
* Move dagu install to first stage
* Fix metrics
* Add DAGs for create dataset from code repository
2023-03-25 00:05:47 +08:00
0f5a959269
Remove tokenizer in testdata/
2023-03-24 09:53:48 +08:00
a0b438da06
Add python transformer backend for tabby (mainly used for local dev / test in non-cuda environment) ( #6 )
...
* Add python backend
* Split docker-compose.triton.yml
* update makefile
2023-03-23 14:14:33 +08:00
df149fad61
Reduce repo size ( #5 )
...
* Remove binary files from git
* Add Makefile
* update
2023-03-23 13:10:59 +08:00
5c5a0ad8c3
Create config dir for config files in deployment
2023-03-22 23:58:55 +08:00
3409a096af
Fix docker-compose.yml
2023-03-22 23:47:35 +08:00
bcce00794e
Add admin panel (w/ streamlit) and logging (w/ vectordev) ( #4 )
2023-03-22 23:18:12 +08:00
Meng Zhang