text-generation-inference/server/exllamav2_kernels/exllamav2_kernels
OlivierDehaene 0d794af6a5
feat: experimental support for cuda graphs (#1428)
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-02-12 10:09:29 +01:00
..
cpp Exllama v2 (#1211) 2023-11-25 22:38:38 +01:00
cuda feat: experimental support for cuda graphs (#1428) 2024-02-12 10:09:29 +01:00
config.h feat: update exllamav2 kernels (#1370) 2023-12-21 17:25:22 +01:00
ext.cpp feat: update exllamav2 kernels (#1370) 2023-12-21 17:25:22 +01:00