mirror/OpenLLM
1
0
Fork 0
mirror of https://github.com/bentoml/OpenLLM.git synced 2026-05-05 14:22:43 -04:00
Code Issues Packages Projects Releases Wiki Activity
112 Commits 6 Branches 194 Tags
64d783107d20f6a15c1921b1b6df287359fa7cbb
Commit Graph

112 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Aaron
64d783107d chore(cli): update namespace and show better traceback 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-03 06:39:01 -07:00
Aaron
ced6faf3c9 fix(runner): quiet warning 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-03 06:37:10 -07:00
Aaron
712590a427 chore(bentoml): using external types export 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-02 16:07:46 -07:00
Aaron
771c93e358 infra: bump to dev version of 0.0.17.dev0 [generated] 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-02 07:07:03 -07:00
Aaron
9b8f84122c infra: prepare for release 0.0.16 [generated] 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
v0.0.16 		2023-06-02 06:58:34 -07:00
Aaron
49cb02d2f2 perf(cli): improve printing speed that respect terminal_size 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-02 06:58:11 -07:00
Aaron
873edc4121 chore(types): improve annotaiton for specified CLI 
improve: Faster CLI improvement, cached hints to __openllm_hints__

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-02 01:01:00 -07:00
aarnphm-ec2-dev
c3aeb43997 fix: generation serde 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-06-02 07:06:04 +00:00
aarnphm-ec2-dev
07d42daaec fix: make sure we evolve the attribute from CLI 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-06-02 05:52:04 +00:00
aarnphm-ec2-dev
a94294bc65 fix: generate attrs class internally to conform with interface 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-06-01 19:06:06 +00:00
Aaron
84358b28cd chore: handle KeyboardInterrupt correctly 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-01 01:23:44 -07:00
Aaron
201afa791b infra: bump to dev version of 0.0.16.dev0 [generated] 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-01 00:29:12 -07:00
Aaron
13cad6709c infra: prepare for release 0.0.15 [generated] 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
v0.0.15 		2023-06-01 00:28:53 -07:00
Aaron
e86dc35ec5 chore: migrate service to use JSON 
until we have attrs io descriptor, this should do it

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-06-01 00:28:43 -07:00
dependabot[bot]
a440bea184 build(deps): Bump bufbuild/buf-setup-action from 1.19.0 to 1.20.0 (#8) 
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2023-05-31 22:18:46 -07:00
Aaron
c33a90a0cc chore: add annotations for attrs and eval correct annotation type 
eval will be here once I find a different way to parse types into
python

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-31 17:11:20 -07:00
Aaron
e910b6d3bd infra: bump to dev version of 0.0.15.dev0 [generated] 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-31 14:12:57 -07:00
Aaron
feb7265c80 infra: prepare for release 0.0.14 [generated] 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
v0.0.14 		2023-05-31 14:12:37 -07:00
Aaron
c2d620c772 fix(load): Make sure we safely load environment variables 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-31 14:12:19 -07:00
Aaron
4e2d5e330c refactor(cli): move CLI to address anti-pattern 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-31 13:53:40 -07:00
Aaron
a72f4d7117 infra: bump to dev version of 0.0.14.dev0 [generated] 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-30 14:56:59 -07:00
Aaron
169a1ca9eb infra: prepare for release 0.0.13 [generated] 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
v0.0.13 		2023-05-30 14:56:41 -07:00
Aaron
33e7004e66 format: consistent CLI outputs 
vendorred type-related module from bentoml._internal.types

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-30 14:56:11 -07:00
Aaron
5b1b7d6ab8 chore(llm): expose langchain API to the runner 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-30 14:37:00 -07:00
Aaron
36ba176bd5 infra: bump to dev version of 0.0.13.dev0 [generated] 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-30 12:02:36 -07:00
Aaron
21eb852242 infra: prepare for release 0.0.12 [generated] 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
v0.0.12 		2023-05-30 12:02:18 -07:00
Aaron
fa16c67131 fix(cli): remove debug print 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-30 12:02:00 -07:00
Aaron
e836218053 infra: bump to dev version of 0.0.12.dev0 [generated] 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-30 12:00:16 -07:00
Aaron
cf1d3b4d55 infra: prepare for release 0.0.11 [generated] 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
v0.0.11 		2023-05-30 11:59:55 -07:00
Aaron Pham
01517e37c6 migration: attrs (#7) 
Move configuration to attrs

Depends on https://github.com/bentoml/BentoML/pull/3906
 2023-05-30 11:59:21 -07:00
Aaron
3e69c49ff0 infra: bump to dev version of 0.0.11.dev0 [generated] 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-28 19:15:41 -07:00
Aaron
ad5d126d95 infra: prepare for release 0.0.10 [generated] 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
v0.0.10 		2023-05-28 19:15:15 -07:00
Aaron
d5f213e49c compat: provide shim for pydantic 1 and 2 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-28 19:14:51 -07:00
Aaron
aff23584a5 docs: jot down some thoughts for API design 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-28 17:04:15 -07:00
Aaron
41706eee5b feat(save_model): passing tag 
update with upstream bentoml

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-28 17:04:15 -07:00
aarnphm-ec2-dev
f68c764f9b chore: disable bettertransformer when bitsandbytes is used 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-05-28 20:09:57 +00:00
aarnphm-ec2-dev
b4b65fc609 chore(stablelm): tuning half when 8bit is not loaded 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-05-28 19:55:26 +00:00
Aaron Pham
ceb9f7bded feat: BetterTransformer during inference (#6) 2023-05-28 11:56:49 -07:00
Aaron
ac710dfd54 revert(perf): remove group alias 
There is no need for this feature

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-28 10:04:33 -07:00
Aaron
454b1edc32 infra: bump to dev version of 0.0.10.dev0 [generated] 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-28 10:00:34 -07:00
Aaron
ef0ddebd60 infra: prepare for release 0.0.9 [generated] 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
v0.0.9 		2023-05-28 10:00:08 -07:00
Aaron
435129372e perf(cli): lazily cached start commands 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-28 09:59:43 -07:00
aarnphm-ec2-dev
9c1c4ca0bf perf(cli): using click instead of rich console 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-28 09:32:56 -07:00
aarnphm-ec2-dev
3f36d81744 infra: docs and normalize formatting 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-05-28 15:00:17 +00:00
aarnphm-ec2-dev
8ca488d8fc fix(stablelm): Ensure passing EOS_TOKEN_ID for generation 
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-05-28 14:43:00 +00:00
Aaron
b4403c24b0 fix(model): Make sure we download the model before starting the 
service

This will ensure we don't deadlock among processes

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
 2023-05-28 14:01:49 +00:00
Aaron
8e8d95cae9 feat: StableLM tuned and alpha 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-28 06:36:06 -07:00
Aaron
99d8e450c2 infra: cleanup unused bazel rules 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-28 06:09:32 -07:00
Aaron
78358dbb8d fix(type): configuration and dependencies 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-28 06:01:30 -07:00
Aaron
0df8d8b9a6 perf: reduce unecessary object creation for config class 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-05-28 05:22:22 -07:00