mirror/OpenLLM
1
0
Fork 0
mirror of https://github.com/bentoml/OpenLLM.git synced 2026-01-17 20:08:17 -05:00
Code Issues Packages Projects Releases Wiki Activity
1,410 Commits 4 Branches 194 Tags
51bec78ee9f57c1e5378bce323aa330a0c433077
Commit Graph

192 Commits

Author SHA1 Message Date
Aaron Pham
51bec78ee9 fix(load): make sure to respect MAX_MODEL_LEN from env 
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
 2024-03-21 07:44:49 +00:00
Aaron
295a3b1061 chore(codegen): update generated var to read from envvar 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2024-03-20 21:51:39 -04:00
Aaron Pham
f0ab6d44fa fix: make sure to include new implementation in bundle build 
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
 2024-03-20 22:11:53 +00:00
Aaron
5c8c30a70b fix: uses --pre for alpha releases for now 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2024-03-20 13:38:10 -04:00
Aaron
2ddbe4eb22 fix(service): remove mounting ASGI app 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2024-03-20 11:51:09 -04:00
Aaron Pham
824ff68818 chore: update local script and update service 
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
 2024-03-15 20:29:49 +00:00
Aaron
727361ced7 chore: running updated ruff formatter [skip ci] 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2024-03-15 05:35:24 -04:00
Aaron
c34db550a6 fix(build): explicit set to use alpha version 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2024-03-15 05:33:18 -04:00
Aaron
0274fb4c11 fix: don't lock openllm to support alpha release 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2024-03-15 05:29:35 -04:00
Aaron Pham
072b3e97ec feat: 1.2 APIs (#821) 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2024-03-15 03:49:19 -04:00
Aaron
e3392476be revert: "ci: pre-commit autoupdate [pre-commit.ci] (#931)" 
This reverts commit 7b00c84c2a.
 2024-03-15 03:47:23 -04:00
pre-commit-ci[bot]
7b00c84c2a ci: pre-commit autoupdate [pre-commit.ci] (#931) 
* ci: pre-commit autoupdate [pre-commit.ci]

updates:
- [github.com/astral-sh/ruff-pre-commit: v0.2.2 → v0.3.2](https://github.com/astral-sh/ruff-pre-commit/compare/v0.2.2...v0.3.2)
- [github.com/pre-commit/mirrors-eslint: v9.0.0-beta.0 → v9.0.0-beta.2](https://github.com/pre-commit/mirrors-eslint/compare/v9.0.0-beta.0...v9.0.0-beta.2)

* ci: auto fixes from pre-commit.ci

For more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2024-03-15 03:46:28 -04:00
Zhao Shenyang
3299f463a6 fix: remove vllm dependency for pytorch bento (#893) 2024-02-05 18:36:14 -05:00
Zhao Shenyang
16d8caf2ee chore: bump up bentoml version to 1.1.11 (#883) 2024-02-04 21:31:14 +08:00
Zhao Shenyang
9d0e292076 fix: limit BentoML version range (#881) 2024-02-04 16:59:21 +08:00
Zhao Shenyang
9f9195f74b fix: all runners sse output (#880) 2024-02-02 20:08:31 +08:00
Zhao Shenyang
6c909aabdb chore: set stop to empty list by default (#878) 2024-02-02 19:28:49 +08:00
Zhao Shenyang
aff5dc8ff2 fix: proper SSE handling for vllm (#877) 
fix: proper SSE handling
 2024-02-02 17:25:58 +08:00
Fazli Sapuan
6b3a1bd708 chore: fix typo in list_models pydoc (#847) 2024-01-15 08:26:48 -05:00
Zhao Shenyang
8baaf122ae improv(package): use python slim base image and let pytorch install cuda (#807) 2024-01-11 23:23:03 -05:00
Aaron Pham
8d63afc9ce feat(vllm): support GPTQ with 0.2.6 (#797) 
* feat(vllm): GPTQ support passthrough

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* chore: run scripts

Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>

* fix(install): set order of xformers before vllm

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* feat: support GPTQ with vLLM

Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>

---------

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
 2023-12-18 12:41:19 -05:00
Aaron Pham
5d27337e82 fix(cli): avoid runtime __origin__ check for older Python (#798) 
fix(cli): avoid runtime __origin__ on older Python

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-12-18 12:33:36 -05:00
Aaron Pham
88b6d3d6de perf: upgrade mixtral to use expert parallelism (#783) 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-12-15 11:45:08 -05:00
Aaron Pham
c8c9663d06 fix(infra): conform ruff to 150 LL (#781) 
Generally correctly format it with ruff format and manual style

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-12-14 17:27:32 -05:00
Aaron Pham
44383528b5 fix(logprobs): correct check logprobs (#779) 
* fix(logprobs): correct check logprobs

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* chore: update changlog

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

---------

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-12-14 14:19:01 -05:00
Aaron Pham
0d83cefcb6 fix(mixtral): setup hack atm to load weights from pt specifically instead of safetensors (#776) 
fix(mixtral): setup hack atm to load weights from pt specifically
instead of safetensors

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-12-13 18:18:51 -05:00
Aaron Pham
2dbcfa8a0c fix(cli): correct set arguments for openllm import and openllm build (#775) 
* fix(cli): correct set arguments for `openllm import` and `openllm build`

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* chore: update changelog

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

---------

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-12-13 15:52:59 -05:00
Aaron Pham
3ab78cd105 feat(mixtral): correct support for mixtral (#772) 
feat(mixtral): support inference with pt

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-12-13 09:03:56 -05:00
Aaron Pham
d3328343d7 feat: mixtral support (#770) 
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
 2023-12-12 01:33:13 -05:00
Aaron
59e8ef93dc chore(deps): lock vLLM to 0.2.4 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-12-12 00:17:18 -05:00
Aaron Pham
08114410bc fix(openai): logprobs when echo is enabled (#761) 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-12-10 18:09:25 -05:00
Aaron Pham
c3a0b5c39f feat(openai): supports echo (#760) 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-12-10 13:19:40 -05:00
Aaron
bb4ed8b53c fix(llm): correct annotations definitions 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-12-09 09:59:02 -05:00
Aaron
9a7e0cecf0 fix(types): makes sures mypy is running strict 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-11-30 09:42:24 -05:00
Aaron
55a0b2f825 fix(style): setup correct block format 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-11-30 07:58:35 -05:00
Aaron
b53559de6f fix(setter): correct item with the same kwargs with stubs 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-11-30 07:36:34 -05:00
yansheng
3cb7f14fc1 feat(models): Support qwen (#742) 
* support qwen

* support qwen

* ci: auto fixes from pre-commit.ci

For more information, see https://pre-commit.ci

* Update openllm-core/src/openllm_core/config/configuration_qwen.py

Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>

* chore: update correct readme and supports qwen models

Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>

---------

Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
Co-authored-by: root <yansheng105@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
 2023-11-30 06:54:17 -05:00
Aaron Pham
0909e08e3c fix(llm): remove unecessary parsing 
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
 2023-11-29 18:00:08 +00:00
Aaron Pham
9706228956 chore(vllm): add arguments for gpu memory utilization 
Probably not going to fix anything, just delaying the problem.

Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
 2023-11-29 06:45:14 +00:00
Aaron Pham
f0fa06004b chore: revert back previous backend support PyTorch (#739) 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-11-29 01:44:41 -05:00
Aaron Pham
d04309188b chore(style): 2.7k 
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
 2023-11-28 07:04:27 +00:00
Aaron
ce6efc2a9e chore(style): cleanup bytes 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-11-28 01:27:27 -05:00
Aaron
96318b65ee fix(sdk): remove broken sdk 
codespace now around 2.8k lines

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-11-26 04:53:36 -05:00
Aaron
43a96dab2c fix(gpus): disable slots for now to enable cached_property 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-11-26 02:49:48 -05:00
Aaron
69aae34cf4 fix(style): reduce boilerplate and format to custom logics 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-11-26 01:44:59 -05:00
Aaron
b4c9971678 fix(build): explicitly not lock packages 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-11-24 01:21:29 -05:00
Aaron
7dd4e3ac4b fix(build): don't lock packages for now, but do lock base requirements 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-11-24 01:17:45 -05:00
Aaron
7beaa92c2b fix(types): using correct refactored literal 
Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-11-24 01:14:29 -05:00
Aaron Pham
aab173cd99 refactor: focus (#730) 
* perf: remove based images

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* chore: update changelog

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* chore: move dockerifle to run on release only

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

* chore: cleanup unused types

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

---------

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>
 2023-11-24 01:11:31 -05:00
Aaron Pham
52a44b1bfa chore: cleanup loader (#729) 
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
 2023-11-22 21:51:51 -05:00