Difference between revisions of "AI compute"
KevinYager (talk | contribs) (Created page with " ==Cloud GPU== * [https://lambdalabs.com/ Lambda] * [https://vast.ai/ Vast AI] * [https://lightning.ai/ Lightning AI] * [https://www.runpod.io/ RunPod] * [https://hpc-ai.com/...") |
KevinYager (talk | contribs) (→Cloud LLM Routers & Inference Providers) |
||
| (18 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
| − | + | =Cloud GPU= | |
| − | |||
* [https://lambdalabs.com/ Lambda] | * [https://lambdalabs.com/ Lambda] | ||
* [https://vast.ai/ Vast AI] | * [https://vast.ai/ Vast AI] | ||
| Line 6: | Line 5: | ||
* [https://www.runpod.io/ RunPod] | * [https://www.runpod.io/ RunPod] | ||
* [https://hpc-ai.com/ HPC-AI] | * [https://hpc-ai.com/ HPC-AI] | ||
| + | |||
| + | =Cloud Training Compute= | ||
| + | * [https://nebius.ai/ Nebius AI] | ||
| + | * [https://glaive.ai/ Glaive AI] | ||
| + | |||
| + | =Cloud LLM Routers & Inference Providers= | ||
| + | * [https://openrouter.ai/ OpenRouter] (open and closed models, no Enterprise tier) | ||
| + | * [https://www.litellm.ai/ LiteLLM] (closed models, Enterprise tier) | ||
| + | * [https://centml.ai/ Cent ML] (open models, Enterprise tier) | ||
| + | * [https://fireworks.ai/ Fireworks AI] (open models, Enterprise tier) | ||
| + | * [https://abacus.ai/ Abacus AI] (open and closed models, Enterprise tier) | ||
| + | * [https://portkey.ai/ Portkey] (open? and closed models, Enterprise tier) | ||
| + | * [https://www.together.ai/ Together AI] (open models, Enterprise tier) | ||
| + | * [https://hyperbolic.xyz/ Hyperbolic AI] (open models, Enterprise tier) | ||
| + | * Huggingface [https://huggingface.co/blog/inference-providers Inference Providers Hub] | ||
| + | |||
| + | ==Multi-model with Model Selection== | ||
| + | * [https://www.notdiamond.ai/ Not Diamond ¬⋄] | ||
| + | * [https://withmartian.com/ Martian] | ||
| + | |||
| + | ==Multi-model Web Chat Interfaces== | ||
| + | * [https://simtheory.ai/ SimTheory] | ||
| + | * [https://abacus.ai/ Abacus AI] [https://chatllm.abacus.ai/ ChatLLM] | ||
| + | * [https://poe.com/about Poe] | ||
| + | |||
| + | ==Multi-model Web Playground Interfaces== | ||
| + | * [https://www.together.ai/ Together AI] | ||
| + | * [https://hyperbolic.xyz/ Hyperbolic AI] | ||
| + | |||
| + | =Local Router= | ||
| + | * [https://ollama.com/ Ollama] | ||
| + | * [https://github.com/mudler/LocalAI LocalAI] | ||
| + | * [https://github.com/AK391/ai-gradio ai-gradio]: unified model interface (based on [https://www.gradio.app/ gradio]) | ||
| + | |||
| + | =Acceleration Hardware= | ||
| + | * [https://www.nvidia.com/ Nvidia] GPUs | ||
| + | * Google [https://en.wikipedia.org/wiki/Tensor_Processing_Unit TPU] | ||
| + | * [https://www.etched.com/ Etched]: Transformer ASICs | ||
| + | * [https://cerebras.ai/ Cerebras] | ||
| + | * [https://www.untether.ai/ Untether AI] | ||
| + | * [https://www.graphcore.ai/ Graphcore] | ||
| + | * [https://sambanova.ai/ SambaNova Systems] | ||
| + | * [https://groq.com/ Groq] | ||
| + | * Tesla [https://en.wikipedia.org/wiki/Tesla_Dojo Dojo] | ||
| + | * [https://deepsilicon.com/ Deep Silicon]: Combined hardware/software solution for accelerated AI ([https://x.com/sdianahu/status/1833186687369023550 e.g.] ternary math) | ||
Latest revision as of 20:25, 5 March 2025
Contents
Cloud GPU
Cloud Training Compute
Cloud LLM Routers & Inference Providers
- OpenRouter (open and closed models, no Enterprise tier)
- LiteLLM (closed models, Enterprise tier)
- Cent ML (open models, Enterprise tier)
- Fireworks AI (open models, Enterprise tier)
- Abacus AI (open and closed models, Enterprise tier)
- Portkey (open? and closed models, Enterprise tier)
- Together AI (open models, Enterprise tier)
- Hyperbolic AI (open models, Enterprise tier)
- Huggingface Inference Providers Hub
Multi-model with Model Selection
Multi-model Web Chat Interfaces
Multi-model Web Playground Interfaces
Local Router
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)
