Try it on a Lightning Studio: http://
Lightning.ai
SOFTWARE
-
Lightning Studio: Try AI Development Platform Today
By
–
-
Perplexity API Coding Assistant Launches on VSCode
By
–
pplx-api powered coding assistant on VSCode! https://t.co/yAxeUMaOuB
— Aravind Srinivas (@AravSrinivas) 19 avril 2024pplx-api powered coding assistant on VSCode!
-
Signal vs WhatsApp: Metadata Protection Differences Explained
By
–
What'sApp uses the Signal Protocol to protect the contents of comms–what you say. But it doesn't protect things like your contact list, profile name, who's in a group chat, who's messaging whom, etc. Signal protects all of these. This is a very important differentiator.
-
Stable Diffusion 3 and SD3 Turbo Now Available on Poe
By
–
Stable Diffusion 3 and the faster SD3 Turbo are hosted by @FireworksAI_HQ and available at SD3 https://
poe.com/StableDiffusio
n3
…, and SD3-Turbo https://
poe.com/SD3-Turbo, and across all Poe apps. We look forward to seeing what you create! (2/2) -
Cursor Copilot++ Gets 40% Speed Boost and Enhanced Capabilities
By
–
We rolled out a major performance upgrade to Cursor's Copilot++ today! The same model ~40% faster now overall, and the performance is especially improved on small edits. Next up for Copilot++: more intelligence, more capabilities, and even more context.
-
torch.compile uses Triton kernels under the hood for optimization
By
–
So if you're using torch.compile you're already using a lot of triton under the hood, afaik PyTorch picks and chooses whether to call cuda kernels or triton for different ops / settings. Triton is really awesome, but of course you're staying in the Python / torch universe. Which
-
Managing Python Dependencies Across Multiple Development Environments
By
–
does anyone else have a requirements.txt that you just keep adding to every time you run into a package you need and carry it over to literally every single env you work in
-
Open Models Drive Rapid AI Capability Improvements and Speed
By
–
Because anyone can work with them, open models are likely to improve very quickly, creating a lot of capabilities focused on factors ranging from speed to costs.
— Ethan Mollick (@emollick) 19 avril 2024
Here is the new Llama 3 70B being served by Groq (with a q) at 224 tokens/second. This is real-time of me using it. pic.twitter.com/L6i6T6OBbWBecause anyone can work with them, open models are likely to improve very quickly, creating a lot of capabilities focused on factors ranging from speed to costs. Here is the new Llama 3 70B being served by Groq (with a q) at 224 tokens/second. This is real-time of me using it.
-
LangChain Weekly Release: Evaluations, Tool Calling, Monitoring
By
–
LangChain Release Notes, week of 4/15 Evaluations video series Standardized tool calling in LangChain Production monitoring and automations in LangSmith New RAG From Scratch videos
Community created content! Read it all here: https://
blog.langchain.dev/week-of-4-15-l
angchain-release-notes/
… -
Groq Serves LLaMA 3 at Record 800 Tokens Per Second
By
–
My mind is blown.@GroqInc is serving LLaMA 3 at over 800 tokens per second!
— Matt Shumer (@mattshumer_) 19 avril 2024
800. Tokens. Per. Second.
This unlocks so many incredible use-cases.
It's one thing to see my demo — it's another thing entirely to experience it for yourself.
Do yourself a favor and try it asap. pic.twitter.com/Rd5NW5SDlWMy mind is blown. @GroqInc is serving LLaMA 3 at over 800 tokens per second! 800. Tokens. Per. Second. This unlocks so many incredible use-cases. It's one thing to see my demo — it's another thing entirely to experience it for yourself. Do yourself a favor and try it asap.