Daya Khudia
Daya Khudia's posts
- AI Research
Fast, Secure and Reliable: Enterprise-grade LLM Inference
14 min read - AI Research
Serving Quantized LLMs on NVIDIA H100 Tensor Core GPUs
7 min read - AI Research
LLM Training and Inference with Intel Gaudi 2 AI Accelerators
15 min read - AI Research
Integrating NVIDIA TensorRT-LLM with the Databricks Inference Stack
3 min read - Engineering
Introducing Mixtral 8x7B with Databricks Model Serving
5 min read - AI Research
LLM Inference Performance Engineering: Best Practices
15 min read - AI Research
Introducing Llama2-70B-Chat with MosaicML Inference
12 min read - AI Research
Benchmarking Large Language Models on NVIDIA H100 GPUs with CoreWeave (Part 1)
7 min read - AI Research
MosaicML Delivers Leading NLP Performance in MLPerf v2.1
3 min read - AI Research
MosaicML Satisfies the Need for Speed with MLPerf Results
4 min read
Get the latest posts in your inbox
Subscribe to our blog and get the latest posts delivered to your inbox.