new: gpu package (#224)

pyproject.toml

@@ -1,5 +1,5 @@
 [tool.poetry]
-name = "fastembed"
+name = "fastembed-gpu"
 version = "0.4.2"
 description = "Fast, light, accurate library built for retrieval embedding generation"
 authors = ["Qdrant Team <[email protected]>", "NirantK <[email protected]>"]
@@ -13,7 +13,7 @@ keywords = ["vector", "embedding", "neural", "search", "qdrant", "sentence-trans
 [tool.poetry.dependencies]
 python = ">=3.8.0,<3.13"
 onnx = "^1.15.0"
-onnxruntime = ">=1.17.0,<1.20.0"
+onnxruntime-gpu = ">=1.17.0,<1.20.0"
 tqdm = "^4.66"
 requests = "^2.31"
 tokenizers = ">=0.15,<1.0"