Skip to content

Commit 9ffc087

Browse files
Merge pull request #29 from shcherbak-ai/dev
docs: v0.5.0 performance note
2 parents eee6b5e + ab5fd99 commit 9ffc087

File tree

4 files changed

+6
-2
lines changed

4 files changed

+6
-2
lines changed

CHANGELOG.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -10,7 +10,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
1010
- Params handling for reasoning (CoT-capable) models other than OpenAI o-series. Enabled automatic retry of LLM calls with dropping unsupported params if such unsupported params were set for the model. Improved handling and validation of LLM call params.
1111

1212
### Changed
13-
- Migrated to wtpsplit-lite - a lightweight version of wtsplit that only retains accelerated ONNX inference of SaT models with minimal dependencies.
13+
- Migrated to wtpsplit-lite - a lightweight version of wtpsplit that only retains accelerated ONNX inference of SaT models with minimal dependencies.
1414

1515
## [0.4.1](https://github.com/shcherbak-ai/contextgem/releases/tag/v0.4.1) - 2025-05-26
1616
### Added

NOTICE

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -30,7 +30,7 @@ Core Dependencies:
3030
- loguru: Logging utility
3131
- pydantic: Data validation
3232
- python-ulid: ULID generation
33-
- wtpsplit-lite: Lightweight version of wtsplit that only retains accelerated ONNX inference of SaT models with minimal dependencies
33+
- wtpsplit-lite: Lightweight version of wtpsplit that only retains accelerated ONNX inference of SaT models with minimal dependencies
3434

3535
Development Dependencies:
3636
- black: Code formatting

README.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -178,6 +178,8 @@ Read more on the project [motivation](https://contextgem.dev/motivation.html) in
178178
pip install -U contextgem
179179
```
180180

181+
> **⚡ v0.5.0+**: ContextGem now installs 7.5x faster with minimal dependencies (no torch/transformers required), making it easier to integrate into existing ML environments.
182+
181183

182184
## 🚀 Quick start
183185

dev/readme.template.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -59,6 +59,8 @@ Read more on the project [motivation](https://contextgem.dev/motivation.html) in
5959
pip install -U contextgem
6060
```
6161

62+
> **⚡ v0.5.0+**: ContextGem now installs 7.5x faster with minimal dependencies (no torch/transformers required), making it easier to integrate into existing ML environments.
63+
6264

6365
## 🚀 Quick start
6466

0 commit comments

Comments
 (0)