From e9207ff6830aa6ae171ae6c2a43ca4bef3522ad3 Mon Sep 17 00:00:00 2001 From: Aaron Pham <29749331+aarnphm@users.noreply.github.com> Date: Sun, 19 Nov 2023 15:41:03 +0000 Subject: [PATCH] infra: prepare for release 0.4.16 [generated] [skip ci] Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com> --- CHANGELOG.md | 15 +++++++++++++++ changelog.d/695.change.md | 1 - changelog.d/698.feature.md | 3 --- openllm-node/package.json | 2 +- openllm-python/CHANGELOG.md | 15 +++++++++++++++ openllm-python/pyproject.toml | 4 ++-- package.json | 2 +- 7 files changed, 34 insertions(+), 8 deletions(-) delete mode 100644 changelog.d/695.change.md delete mode 100644 changelog.d/698.feature.md diff --git a/CHANGELOG.md b/CHANGELOG.md index 2339c5dd..2559b1cd 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -18,6 +18,21 @@ This changelog is managed by towncrier and is compiled at release time. +## [0.4.16](https://github.com/bentoml/openllm/tree/v0.4.16) + +### Changes + +- Update vLLM to 0.2.2, bringing supports and a lot of improvement upstream + [#695](https://github.com/bentoml/openllm/issues/695) + + +### Features + +- Added experimental CTranslate backend to run on CPU, that yields higher TPS comparing to PyTorch counterpart. + + This has been tested on c5.4xlarge instances + [#698](https://github.com/bentoml/openllm/issues/698) + ## [0.4.15](https://github.com/bentoml/openllm/tree/v0.4.15) ### Features diff --git a/changelog.d/695.change.md b/changelog.d/695.change.md deleted file mode 100644 index af4f2d7a..00000000 --- a/changelog.d/695.change.md +++ /dev/null @@ -1 +0,0 @@ -Update vLLM to 0.2.2, bringing supports and a lot of improvement upstream diff --git a/changelog.d/698.feature.md b/changelog.d/698.feature.md deleted file mode 100644 index 72238d64..00000000 --- a/changelog.d/698.feature.md +++ /dev/null @@ -1,3 +0,0 @@ -Added experimental CTranslate backend to run on CPU, that yields higher TPS comparing to PyTorch counterpart. - -This has been tested on c5.4xlarge instances diff --git a/openllm-node/package.json b/openllm-node/package.json index 8c293967..92d65ef0 100644 --- a/openllm-node/package.json +++ b/openllm-node/package.json @@ -1,6 +1,6 @@ { "name": "@bentoml/openllm-node", - "version": "0.4.16.dev0", + "version": "0.4.16", "description": "NodeJS library for OpenLLM", "type": "module", "repository": { diff --git a/openllm-python/CHANGELOG.md b/openllm-python/CHANGELOG.md index 2339c5dd..2559b1cd 100644 --- a/openllm-python/CHANGELOG.md +++ b/openllm-python/CHANGELOG.md @@ -18,6 +18,21 @@ This changelog is managed by towncrier and is compiled at release time. +## [0.4.16](https://github.com/bentoml/openllm/tree/v0.4.16) + +### Changes + +- Update vLLM to 0.2.2, bringing supports and a lot of improvement upstream + [#695](https://github.com/bentoml/openllm/issues/695) + + +### Features + +- Added experimental CTranslate backend to run on CPU, that yields higher TPS comparing to PyTorch counterpart. + + This has been tested on c5.4xlarge instances + [#698](https://github.com/bentoml/openllm/issues/698) + ## [0.4.15](https://github.com/bentoml/openllm/tree/v0.4.15) ### Features diff --git a/openllm-python/pyproject.toml b/openllm-python/pyproject.toml index ade45827..ba87f702 100644 --- a/openllm-python/pyproject.toml +++ b/openllm-python/pyproject.toml @@ -40,8 +40,8 @@ classifiers = [ dependencies = [ "bentoml[io]>=1.1.9", "transformers[torch,tokenizers]>=4.35.0", - "openllm-client>=0.4.15", - "openllm-core>=0.4.15", + "openllm-client>=0.4.16", + "openllm-core>=0.4.16", "safetensors", "optimum>=1.12.0", "accelerate", diff --git a/package.json b/package.json index e28515b3..b6388ff3 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "@bentoml/openllm-monorepo", - "version": "0.4.16.dev0", + "version": "0.4.16", "description": "OpenLLM: Operating LLMs in production", "author": "Aaron Pham <29749331+aarnphm@users.noreply.github.com>", "license": "Apache-2.0",