text-generation-inference/server/exllamav2_kernels/exllamav2_kernels
OlivierDehaene 0c207f71ed feat: experimental support for cuda graphs (#1428)
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-04-24 13:15:45 +03:00
..
cpp Exllama v2 (#1211) 2023-11-25 22:38:38 +01:00
cuda feat: experimental support for cuda graphs (#1428) 2024-04-24 13:15:45 +03:00
config.h feat: update exllamav2 kernels (#1370) 2024-04-22 09:02:53 +03:00
ext.cpp feat: update exllamav2 kernels (#1370) 2024-04-22 09:02:53 +03:00