AI compute
Revision as of 14:57, 9 February 2025 by KevinYager (talk | contribs) (→Cloud LLM Routers & Inference Providers)
Contents
Cloud GPU
Cloud Training Compute
Cloud LLM Routers & Inference Providers
- OpenRouter
- LiteLLM
- Cent ML
- Fireworks AI
- Huggingface Inference Providers Hub
Multi-model Web Chat Interfaces
Multi-model Web Playground Interfaces
Acceleration Hardware
- Nvidia GPUs
- Google TPU
- Etched: Transformer ASICs
- Cerebras
- Untether AI
- Graphcore
- SambaNova Systems
- Groq
- Tesla Dojo
- Deep Silicon: Combined hardware/software solution for accelerated AI (e.g. ternary math)