Commit Graph

110 Commits (0a66a9d498e232407850537f1d18142046bd66d4)

Author SHA1 Message Date
Meng Zhang 0a66a9d498 feat: support MODEL_REPLICA to control number of model instances in triton 2023-04-02 13:19:09 +08:00
Meng Zhang 2cda4fd07b feat: add skypilot.yml for skypilot (https://github.com/skypilot-org/skypilot) deployment 2023-04-02 13:09:49 +08:00
Meng Zhang 6877a071ec Cleanup environment variable in tabby.server 2023-04-02 12:11:49 +08:00
Meng Zhang 0a30165862 feat: support load_in_8bits in python backend 2023-04-02 11:54:28 +08:00
Meng Zhang 82103e7280 style: stopwords -> stop_words 2023-04-02 11:26:43 +08:00
Meng Zhang 78280d44bf
Revert stop words implementation in python
#33
2023-03-30 14:52:04 +08:00
Meng Zhang bfcdfd5b7e
Update README.md 2023-03-30 06:16:05 +08:00
Meng Zhang be4eff7fbf
Update README.md 2023-03-29 21:03:07 +08:00
Meng Zhang 3c47760d74
Add bitsandbytes (#35) 2023-03-29 20:47:44 +08:00
Meng Zhang 9dce88497b
Update README.md 2023-03-29 20:44:54 +08:00
Meng Zhang be7894a5e6
feat: support stopping words in python backend. (#32)
* Improve python backend

* Update lockfile

* Support stop words in python backend

* Support LanguagePresets for triton

* Update pre-commit
2023-03-29 20:23:11 +08:00
Zhiming Ma 2f31418ac6
VSCode client: Add status bar item. (#31) 2023-03-29 18:30:13 +08:00
Meng Zhang a5afed584f Only install pre-commit in setup-development-environment 2023-03-29 17:04:10 +08:00
Meng Zhang 477ef83319 Update startup_periord to 1200s as a HF model download might take time 2023-03-29 16:45:46 +08:00
Meng Zhang 2bcc4d649f Add supervisord.pid to gitignore 2023-03-29 16:41:18 +08:00
Meng Zhang e0b85c82d7 Rename duckdb to analytic 2023-03-29 16:38:59 +08:00
Meng Zhang 20801bbe8c
Cleanup environment variable (#30)
* Remove EVENTS_LOG_DIR

* Rename supervisord.sh -> tabby.sh
2023-03-29 16:33:00 +08:00
Meng Zhang 44ac6cd510
Update README.md 2023-03-29 13:30:17 +08:00
Meng Zhang 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
Meng Zhang 07a3cff13a
Delete README.md 2023-03-29 09:09:41 +08:00
Meng Zhang 5b12b36a1a
Update README.md 2023-03-28 21:06:45 +08:00
Meng Zhang 7d3225501a
Update README.md 2023-03-28 21:06:28 +08:00
Meng Zhang 03f70c8466
move vscode clients (#27) 2023-03-28 20:35:59 +08:00
Meng Zhang 2e24deef12 Remove unused files 2023-03-28 20:30:35 +08:00
Meng Zhang 0aa422cb3e Remove unused docker-compose.triton.yml 2023-03-28 20:30:03 +08:00
Meng Zhang 490a1e154d Cleanup development settings 2023-03-28 20:28:20 +08:00
Meng Zhang 648d521afb
Update README.md 2023-03-28 20:12:39 +08:00
Meng Zhang 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
Meng Zhang 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
Meng Zhang 81baf7f3c6
Update README.md 2023-03-28 16:31:54 +08:00
Meng Zhang 92eb2d54f5
Add LoRA Fine-tuning for private code repository (#22)
* Add bitandsands

* Fix cudart in Dockerfile

* Add ConstantLengthDataset in trainer

* Add train_lora

* Remove bnb

* Remove useless imports
2023-03-28 15:57:13 +08:00
Zhiming Ma e992a0144b
Add client: VSCode. (#21) 2023-03-28 15:53:57 +08:00
Meng Zhang c990ba843f Extract environment variable 2023-03-27 13:42:06 +08:00
Meng Zhang ac0bcd39eb
Update README.md 2023-03-27 13:26:59 +08:00
Meng Zhang f299bac4d8
Update README.md 2023-03-27 13:26:03 +08:00
Meng Zhang 13b833efd4 Add clean 2023-03-27 13:13:06 +08:00
Meng Zhang 5b6125d89e Add Development 2023-03-27 13:07:41 +08:00
Meng Zhang eacafd63a5
Update README.md 2023-03-27 12:59:08 +08:00
Meng Zhang f15624ff8b
Delete docs directory 2023-03-27 12:54:45 +08:00
Meng Zhang 22437c8e4b
Update README.md 2023-03-27 12:54:37 +08:00
Meng Zhang d28d133d0f
Update README.md 2023-03-27 12:48:58 +08:00
Meng Zhang 5a5d3e447d
Update README.md 2023-03-27 12:48:16 +08:00
Meng Zhang 07b742befd
Update README.md 2023-03-27 12:47:40 +08:00
Meng Zhang 947c1638dd
Update README.md 2023-03-27 12:45:59 +08:00
Meng Zhang 3e9cbc0219
Update README.md 2023-03-27 12:09:07 +08:00
Meng Zhang d5d58fbbec
Improve documentations. (#20)
* Improve help message of model preload

* Update development/scripts/triton.sh

* Improve documents

* Update deployment.md

* Update deployment.md
2023-03-27 11:46:18 +08:00
Meng Zhang 9d92821cf5
Add gptj converter (#19)
* Rename deployment-next to development

* Add GPTJ converter
2023-03-27 11:12:52 +08:00
Meng Zhang d796476013
Update README.md 2023-03-27 09:38:24 +08:00
Meng Zhang 92ddbe8705
Update README.md 2023-03-27 01:12:37 +08:00
Meng Zhang 9739683fba
Switch default deploy model (#18) 2023-03-27 01:10:15 +08:00