Mattias Dürrmeier
mattduerrmeier
webbrain-one-447637's profile picture
Dinewo-Nyathi2's profile picture
webbrain-sdj3euiu's profile picture·
AI & ML interests
LLM Inference, faster and more efficient kernels, local inference
Recent Activity
authored a paper 3 days ago
Local Inference of LLMs on Long Contexts: A Data Systems Perspective upvoted an article 3 days ago
Carbon-A: Finding genes in known and unknown genomes upvoted a paper 17 days ago
Local Inference of LLMs on Long Contexts: A Data Systems PerspectiveOrganizations
-
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
Paper • 2602.24286 • Published • 95 -
FlashFormer: Whole-Model Kernels for Efficient Low-Batch Inference
Paper • 2505.22758 • Published • 1 -
Liger Kernel: Efficient Triton Kernels for LLM Training
Paper • 2410.10989 • Published • 3 -
FlashDecoding++: Faster Large Language Model Inference on GPUs
Paper • 2311.01282 • Published • 34
-
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
Paper • 2602.24286 • Published • 95 -
FlashFormer: Whole-Model Kernels for Efficient Low-Batch Inference
Paper • 2505.22758 • Published • 1 -
Liger Kernel: Efficient Triton Kernels for LLM Training
Paper • 2410.10989 • Published • 3 -
FlashDecoding++: Faster Large Language Model Inference on GPUs
Paper • 2311.01282 • Published • 34
models 0
None public yet
datasets 0
None public yet