Baseten Joins Hugging Face as Official Inference Provider
baseten · x · 2026-08-06
AI infrastructure platform Baseten has officially joined Hugging Face's ecosystem as a supported Inference Provider. Users can now run popular open-weight LLMs like Kimi K3, DeepSeek V4 Flash, and GLM-5.2 directly from HF model pages or via the SDK using their HF tokens.
The initial integration focuses on conversational and text-generation tasks, with support for additional modalities rolling out soon. Developers can configure custom API keys in their HF settings or route requests through HF, ordering providers by preference.
Related event: Baseten Becomes Official Hugging Face Inference Provider(2 posts)→
More from Infra
- Truespar Launches Paddock: High-Performance Local LLM Engine for NVIDIA GPUs — wandedob · 2026-08-06
- SpaceX Announces Terafab Semiconductor Plant to Meet 1TW Compute Demand — RachelVT42 · 2026-08-06
- Breaking the AI Memory Wall: CXL Moves Toward Commercial Deployment — BenBajarin · 2026-08-06
- Redefining Productivity: 'Intelligence Per Watt' (IPW) as the New Economic Metric — NinaDSchick · 2026-08-06
- Rack-Scale AI Infrastructure Accounts for Only ~10% of Installed Base — BenBajarin · 2026-08-06
- Brevis Treats Lossless Tensor Compression as Program Synthesis, Cutting Storage by 33% — SingaporeManagementUniversity · 2026-08-06