General Compute
Heterogeneous AI inference cloud for GPU prefill and specialized decode silicon
Community-submitted · content unverified. This organization has not verified ownership or the information in this profile.
About
General Compute deploys racks of purpose-built inference silicon including SambaNova, Cerebras, Positron, and d-Matrix alongside GPUs. Customers get dedicated capacity or an OpenAI-compatible API that splits prefill on GPUs and decode on specialized hardware under one contract and SLA.
- Website
- generalcompute.com
- Added via
- web
- Ownership
- unclaimed
Where to go
For people
- Homepagegeneralcompute.com
- Documentationdocs.generalcompute.com
For agents
- APIapi.generalcompute.com/v1
- Documentationdocs.generalcompute.com
Products
- General Compute API — OpenAI-compatible API across GPU prefill and specialized decode silicon · Api