v1.4.0

Notable Changes

• Cuda support for the Qwen2 model architecture

What's Changed

• feat(candle): support Qwen2 on Cuda by @OlivierDehaene in https://github.com/huggingface/text-embeddings-inference/pull/316
• fix(candle): fix last token pooling

Full Changelog: https://github.com/huggingface/text-embeddings-inference/compare/v1.3.0...v1.4.0