🏁 Interested in multi-node inference on VLLM? 🏁 Experience in writing faster kernels for training and inference performance? 🏁 Pushing the boundaries of speculative decoding? 🏁 Want to jointly optimize system performance and model architecture? 🏁 Multi-turn KV caching sound fascinating? If this is you, we'd love to talk to you about our inference and training optimization research efforts at Snowflake AI with Cortex. DM me for details ...
Hi Vivek Raghunathan Sir kindly please accept my connection request.
Product @ Weights & Biases - The AI Developer Platform
3wAmazing what you are doing, Vivek. Great opportunity to join his team.