flexflow / FlexFlow

FlexFlow Serve: Low-Latency, High-Performance LLM Serving
https://flexflow.readthedocs.io
Apache License 2.0
1.59k stars 218 forks source link

Change datatype for linear kernels away from `void *` in `.cc` #1397

Open reyna-abhyankar opened 1 month ago

reyna-abhyankar commented 1 month ago

cublasGemmEx takes a bunch of void * and then the appropriate datatype. We should move the cast for the actual datatype to void * in the kernel code.