Sublime
An inspiration engine for ideas
We’re excited to release our webinar featuring OpenDevin - an open-source platform for building autonomous AI engineers.
Robert Brennan, one of the lead maintainers, gives a fantastic walkthrough of the platform, and we discuss some high-level insights for building agents:
- Have specialized “micro”-agents... See more
Yesterday @nvidia delivered one of the first DGX B200s to @OpenAI. The specs for these beasts are insane. https://t.co/OhB7NdLk04
Former $NVDA employee sharing his thoughts on the current GPU "craze":
- He believes inference is becoming increasingly important as people have almost finished the trial-and-error period to instrument the network and train it. Inference will face big challenges with large memory... See more
#ai-video
Karol Dębkowski • 2 cards
📢 Announcing our new speculative decoding framework Sequoia ❗️❗️❗️
It can now serve Llama2-70B on one RTX4090 with half-second/token latency (exact❗️no approximation)
🤔Sounds slow as a sloth 🦥🦥🦥???
Fun fact😛:
DeepSpeed -> 5.3s / token;
8 x A100:... See more
Beidi Chenx.com