flashinfer topic
List
flashinfer repositories
decoding_attention
46
Stars
4
Forks
46
Watchers
Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.
whl
17
Stars
4
Forks
17
Watchers
Kernel Library Wheel for SGLang