biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
Files
bd99d226295776011f4ea4831498a7103bc4e43b
vllm/csrc/quantization/fp8/fp8_cuda_kernels.cu
Philipp Moritz 12628d3c78 [Kernel] Optimize FP8 support for MoE kernel / Mixtral via static scales (#4343) 
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2024-04-27 04:49:59 +00:00

3.8 KiB
Raw Blame History

View Raw
Reference in New Issue View Git Blame Copy Permalink