Kyle Sayers

kylesayrs

·

https://github.com/kylesayrs

AI & ML interests

Accelerating ML inference @ Red Hat

Recent Activity

updated a model about 12 hours ago

RedHatAI/Llama-3.2-1B-Instruct-FP8

updated a collection about 14 hours ago

updated a model 3 days ago

inference-optimization/Qwen3.8-1.0B-A0.6B-NVFP4-FP8

View all activity

Organizations

upvoted a paper about 1 year ago

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

Paper • 2505.14669 • Published May 20, 2025 • 79

upvoted a collection over 1 year ago

Qwen2.5-VL

Vision-language model series based on Qwen2.5 • 10 items • Updated Mar 2 • 568

upvoted a paper almost 2 years ago

"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization

Paper • 2411.02355 • Published Nov 4, 2024 • 52