mirror/OpenLLM
1
0
Fork 0
mirror of https://github.com/bentoml/OpenLLM.git synced 2026-01-23 15:01:32 -05:00
Code Issues Packages Projects Releases Wiki Activity
465 Commits 6 Branches 194 Tags
5f874da4e2cb9aebd3030effebfa8ff694602c55
Commit Graph

62 Commits

Author SHA1 Message Date
aarnphm-ec2-dev
5f874da4e2 fix: broken logics for upload 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-07-19 23:55:35 +00:00
aarnphm-ec2-dev
4beb040cfd chore(ci): remove macos packaging 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-07-19 23:35:49 +00:00
aarnphm-ec2-dev
9d28e0a1e6 fix(ci): disable gpg push 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-07-19 23:09:27 +00:00
aarnphm-ec2-dev
e319a2977f fix(ci): editable install 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-07-19 22:29:29 +00:00
Aaron Pham
c1ddb9ed7c feat: GPTQ + vLLM and LlaMA (#113) 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2023-07-19 18:12:12 -04:00
dependabot[bot]
9833d2f46f fix(ci): correct setup tests and auto-bot (#118) 
Bump pypa/gh-action-pypi-publish from 1.8.7 to 1.8.8

Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-07-17 14:37:46 -04:00
aarnphm-ec2-dev
d37d14e52b fix(tests): mark package on CI to xfail 
XXX: @aarnphm to solve build isolation when have bandwidth. Currently
this is not a problem when running locally.

`openllm build` just works, where as `openllm.build` won't work
sequentially.

Address some type stubs for jupytext

Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-07-15 12:48:28 +00:00
Aaron Pham
b2dba6143f fix(resource): correctly parse CUDA_VISIBLE_DEVICES (#114) 2023-07-15 07:19:35 -04:00
Aaron Pham
c7f4dc7bb2 feat(test): snapshot testing (#107) 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2023-07-10 17:23:19 -04:00
aarnphm-ec2-dev
d3e4b95e84 ci: use trusted pypi publisher 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-07-07 07:18:13 +00:00
Aaron
ec4293091d ci: wait for auto-bot to run check 
only run evergreen on PR

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-07-05 10:53:45 -04:00
Aaron
0892d10436 ci: increase postBuffer for release action 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-07-05 09:08:13 -04:00
Aaron Pham
59b1d89971 feat: custom dockerfile templates (#95) 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2023-06-30 13:44:11 -04:00
Aaron
c5977c8fdd chore(ci): add checkout version for 3.11 and sign push 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-29 02:55:33 -04:00
Aaron
c76dea468e chore(ci): fixes release script to correct version 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-29 02:38:44 -04:00
Aaron
03bc04216b fix(ci): fetch correct tags for branch 
This reverts commit 47e49186e1d2b2bcca0153db1cd47efecbbbf82b.

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-29 00:41:05 -04:00
Aaron
7de2298f21 revert: "fix(ci): release and correct fetch tags in workflow_call" 
This reverts commit 583e11196efb318e95a459a46d630d3d92ae42bf.

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-29 00:41:05 -04:00
Aaron
a411509ee2 fix(ci): release and correct fetch tags in workflow_call 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-29 00:41:05 -04:00
aarnphm-ec2-dev
698d929522 tests: add dict protocol cases 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-06-28 04:25:09 +00:00
Aaron
e8f6ef12e3 fix(ci): release to checkout tag 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-27 14:07:52 -04:00
Aaron Pham
db1494a6ae feat(start): starting bento and fix load (#80) 2023-06-27 12:45:17 -04:00
Aaron
77cb8516b6 fix(ci): pre-commit [skip ci] 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-26 23:46:24 -04:00
aarnphm-ec2-dev
2bb3b26a88 chore(ci): add jobs to cleanup PR cache after complete 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-06-27 03:41:05 +00:00
aarnphm-ec2-dev
45b0ba3b7d fix(ci): outputs jobs for checkout tag on release-notes 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-06-27 01:46:31 +00:00
aarnphm-ec2-dev
76e88048ba chore: fix name 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-06-27 00:18:09 +00:00
Aaron Pham
063c887e1f fix: binary should release on tag not dev (#76) 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-06-27 00:07:55 +00:00
Aaron
96aa9e39ca fix(ci): remove windows packaging if logic 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-06-27 00:07:54 +00:00
Aaron
7a307b8e7d chore: disable building binary 
Only run binary distribution on dispatch or call

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-26 17:49:27 -04:00
Aaron Pham
d544764386 feat: cascading resource strategies (#72) 2023-06-26 17:38:49 -04:00
Aaron
0c39435ed9 chore: remove cron for tests 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-25 22:38:53 -04:00
Aaron
2fed9eae78 ci: signed commit on actions 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-25 12:47:30 -04:00
Aaron
dfaf5d206a fix(ci): sequential chaining 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-25 11:30:59 -04:00
Aaron
4ca8e3e6c1 ci: manually dispatch reusable actions from CLI 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-25 11:27:56 -04:00
Aaron Pham
74fdd5e259 feat: release binary distribution (#66) 2023-06-25 10:38:03 -04:00
Aaron Pham
f0773f2d01 chore: add more test matrices (#70) 2023-06-25 03:44:03 -04:00
Aaron Pham
acb6a3cb32 fix: converting envvar to string (#68) 2023-06-25 03:40:45 -04:00
Aaron Pham
3593c764f0 fix(test): robustness (#64) 2023-06-24 11:10:07 -04:00
Aaron Pham
03758a5487 fix(tools): adhere to style guidelines (#31) 2023-06-18 20:03:17 -04:00
Aaron Pham
6f724416c0 perf: build quantization and better transformer behaviour (#28) 
Fixes quantization_config and low_cpu_mem_usage to be available on PyTorch implementation only

See changelog for more details on #28
 2023-06-17 08:56:14 -04:00
Aaron Pham
ded8a9f809 feat: quantization (#27) 2023-06-16 18:10:50 -04:00
Aaron Pham
f8ebb36e15 tests: fastpath (#17) 
added fastpath cases for configuration and Flan-T5

fixes respecting model_id into lifecycle hooks.

update CLI to cleanup models info
 2023-06-12 14:18:26 -04:00
Aaron
71198b66cc revert: move release-notes to separate actions 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-08 16:03:41 -04:00
Aaron
20bc9153b1 fix(ci): checkout version on actions 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-08 14:40:38 -04:00
Aaron
0680059a21 chore(ci): cleanup workflow 
make it a pipeline for release now

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-08 05:28:56 -04:00
Aaron
ce7143060e chore(ci): to run release note on all tag 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-07 00:24:25 -04:00
Aaron
2a778a6fa6 fix(ci): update detached HEAD to main 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-06 18:23:50 -04:00
Aaron
f78d55f0fd fix(cli): type handling for specific container types 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-06 17:18:25 -04:00
Aaron
f5ab01f2dd infra(release): update logic on push 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-06 09:16:37 -04:00
Aaron
44ac29b9dd infra: update release scripts to run on actions only 
setup release notes to make sure it runs after pushing tag

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-06 08:45:51 -04:00
Aaron
ec941c95d5 chore: add license header 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-04 16:22:37 -07:00