Kernel benchmarks script

SqueezeBits / QUICK

QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference

MIT License

109 stars 6 forks source link

Open shiqingzhangCSU opened 7 months ago

shiqingzhangCSU commented 7 months ago

I want to reproduce the performance of the kernel. Can you upload the Kernel benchmarks script?