Skip to content

sycl : port multi-column MMVQ from CUDA backend

113d79e
Select commit
Loading
Failed to load commit list.
Sign in for the full log view
Merged

sycl : port multi-column MMVQ from CUDA backend (~45% speculative decoding speedup on Intel Arc) #21845

sycl : port multi-column MMVQ from CUDA backend
113d79e
Select commit
Loading
Failed to load commit list.