From e733fd55dcdd36f03fed935cf72e3a15af142455 Mon Sep 17 00:00:00 2001 From: Aaron Pham <29749331+aarnphm@users.noreply.github.com> Date: Sun, 25 Jun 2023 17:55:43 +0000 Subject: [PATCH] infra: prepare for release 0.1.14 [generated] Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com> --- CHANGELOG.md | 40 +++++++++++++++++++++++++++++++++++++++ changelog.d/60.fix.md | 8 -------- changelog.d/64.fix.md | 4 ---- changelog.d/66.feature.md | 15 --------------- package.json | 2 +- src/openllm/__about__.py | 2 +- 6 files changed, 42 insertions(+), 29 deletions(-) delete mode 100644 changelog.d/60.fix.md delete mode 100644 changelog.d/64.fix.md delete mode 100644 changelog.d/66.feature.md diff --git a/CHANGELOG.md b/CHANGELOG.md index b765d79f..8ee70f40 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -18,6 +18,46 @@ This changelog is managed by towncrier and is compiled at release time. +## [0.1.14](https://github.com/bentoml/openllm/tree/v0.1.14) + +### Features + +- Added support for standalone binary distribution. Currently works on Linux and + Windows: + + The following are supported: + + - aarch64-unknown-linux-gnu + - x86_64-unknown-linux-gnu + - x86_64-unknown-linux-musl + - i686-unknown-linux-gnu + - powerpc64le-unknown-linux-gnu + - x86_64-pc-windows-msvc + - i686-pc-windows-msvc + + Reverted matrices expansion for CI to all Python version. Now leveraging Hatch + env matrices + [#66](https://github.com/bentoml/openllm/issues/66) + + +### Bug fix + +- Moved implementation of dolly-v2 and falcon serialization to save PreTrainedModel instead of pipeline. + + Save dolly-v2 now save the actual model instead of the pipeline abstraction. If you have a Dolly-V2 + model available locally, kindly ask you to do `openllm prune` to have the new implementation available. + + Dolly-v2 and falcon nows implements some memory optimization to help with loading with lower resources system + + Configuration removed field: 'use_pipeline' + [#60](https://github.com/bentoml/openllm/issues/60) +- Remove duplicated class instance of `generation_config` as it should be set via + instance attributes. + + fixes tests flakiness and one broken cases for parsing env + [#64](https://github.com/bentoml/openllm/issues/64) + + ## [0.1.13](https://github.com/bentoml/openllm/tree/v0.1.13) No significant changes. diff --git a/changelog.d/60.fix.md b/changelog.d/60.fix.md deleted file mode 100644 index 43e66df0..00000000 --- a/changelog.d/60.fix.md +++ /dev/null @@ -1,8 +0,0 @@ -Moved implementation of dolly-v2 and falcon serialization to save PreTrainedModel instead of pipeline. - -Save dolly-v2 now save the actual model instead of the pipeline abstraction. If you have a Dolly-V2 -model available locally, kindly ask you to do `openllm prune` to have the new implementation available. - -Dolly-v2 and falcon nows implements some memory optimization to help with loading with lower resources system - -Configuration removed field: 'use_pipeline' diff --git a/changelog.d/64.fix.md b/changelog.d/64.fix.md deleted file mode 100644 index 0f4fc32b..00000000 --- a/changelog.d/64.fix.md +++ /dev/null @@ -1,4 +0,0 @@ -Remove duplicated class instance of `generation_config` as it should be set via -instance attributes. - -fixes tests flakiness and one broken cases for parsing env diff --git a/changelog.d/66.feature.md b/changelog.d/66.feature.md deleted file mode 100644 index dde49763..00000000 --- a/changelog.d/66.feature.md +++ /dev/null @@ -1,15 +0,0 @@ -Added support for standalone binary distribution. Currently works on Linux and -Windows: - -The following are supported: - -- aarch64-unknown-linux-gnu -- x86_64-unknown-linux-gnu -- x86_64-unknown-linux-musl -- i686-unknown-linux-gnu -- powerpc64le-unknown-linux-gnu -- x86_64-pc-windows-msvc -- i686-pc-windows-msvc - -Reverted matrices expansion for CI to all Python version. Now leveraging Hatch -env matrices diff --git a/package.json b/package.json index 4c22c669..57c0e74e 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "openllm", - "version": "0.1.14.dev0", + "version": "0.1.14", "description": "OpenLLM: Your one stop-and-go solution for serving Large Language Model", "repository": "git@github.com:llmsys/OpenLLM.git", "author": "Aaron Pham <29749331+aarnphm@users.noreply.github.com>", diff --git a/src/openllm/__about__.py b/src/openllm/__about__.py index b91660de..126d4ba8 100644 --- a/src/openllm/__about__.py +++ b/src/openllm/__about__.py @@ -11,4 +11,4 @@ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. -__version__ = "0.1.14.dev0" +__version__ = "0.1.14"