Posts
-
Accelerate LLM Inference with Open Kernels and Smarter Autotuning with FlashInfer v0.7
-
MegaMoE in FlashInfer: Fused Expert-Parallel MoE Kernels
-
Move Fast. Don’t Break Things.
-
FlashInfer Autotuner v2: Tune the Way You Serve
-
FlashInfer-Bench: Building the Virtuous Cycle for AI-driven LLM Systems
-
Sorting-Free GPU Kernels for LLM Sampling
-
FlashInfer 0.2 - Efficient and Customizable Kernels for LLM Inference Serving
-
Cascade Inference: Memory Bandwidth Efficient Shared Prefix Batch Decoding
-
Accelerating Self-Attentions for LLM Serving with FlashInfer
subscribe via RSS