Hugging Face Inference Endpoints
Named by 4 kept items in this workspace.
Search every workspace for Hugging Face Inference Endpoints. It matches the name as written, so it can find other things that share it.
The items that name it 4
Managed deployment of Mistral Large 4, with a recipe on 8 x NVIDIA H200 GPUs running vLLM with FP8 weights.
One-click deploy of Beam in FP8 or NVFP4 from the catalog, or via hf cli
Managed deployment with a pre-validated SGLang recipe for NVFP4, exposing Chat Completions and Responses APIs.
Serves low-latency embeddings for live queries and incremental updates; deployed as an authenticated endpoint backed by TEI, configurable to scale to zero when idle
All technologies in this workspace.