LitServe: Build custom AI inference enginesgithub.com1 points·by wfalcon·9 maanden geleden·0 comments
Agent sandbox: safe, persistent cloud environments for agentslightning.ai2 points·by wfalcon·vorig jaar·1 comments
Lightning AI hub: Production AI in your cloud in minuteslightning.ai16 points·by wfalcon·vorig jaar·0 comments
Deploy dedicated DeepSeek 32B on L40 GPUs ($8/hour)lightning.ai19 points·by wfalcon·vorig jaar·6 comments
I'm crazy: I deployed DeepSeek in my company VPC in <24 hours without Kuberneteslightning.ai5 points·by wfalcon·vorig jaar·2 comments
Deploy a custom Llama 3 API in 15 lines of codelightning.ai1 points·by wfalcon·2 jaar geleden·0 comments
Thunder – A new compiler for PyTorch that can use many device executors at oncegithub.com11 points·by wfalcon·2 jaar geleden·1 comments
wfalcon·vorig jaar·discussStudios are a great google colab alternative with:- persistent storage (setup env and data persists across restarts)- free ssh and connect your local IDE- CPU setup, GPU run (do setup work on CPUs and switch to run on a GPU when ready)- no credit card- pay-as-you-go if you need more GPU hours- A100s, H100s, and more GPUs available
wfalcon·2 jaar geleden·discussthis is also what our (Lightning AI) lit-gpt library does. https://github.com/Lightning-AI/lit-gpt
- persistent storage (setup env and data persists across restarts)
- free ssh and connect your local IDE
- CPU setup, GPU run (do setup work on CPUs and switch to run on a GPU when ready)
- no credit card
- pay-as-you-go if you need more GPU hours
- A100s, H100s, and more GPUs available