huggingface/text-embeddings-inference Issues
CUDA_ERROR_OUT_OF_MEMORY
Closed 3Images Embeddings (ex. CLIP model)
Updated 2GPU memory usage is limited
Closed 4Unknown variant Qwen2
Closed 2Support tokenized input
Updated 2Support gte-Qwen1.5-7B-instruct
Updated 1Support nvidia/NV-Embed-v1
Closed 2Adding a cache layer
Closed 3Deberta V3 not supported
Updated 1Too much cpu memory consumption
Closed 2Support NER models
Closed 1Connection Error
ClosedModel downloads just *hang*
Closed 1Multiple Model Endpoint support
Closed 1Missing CONTRIBUTING.md
Closed 2very high cadinality metrics
Closed 2Call for benchmark
Updated