text-generation-inference/server/exllama_kernels
2023-07-24 11:43:58 +02:00
..
exllama_kernels feat(server): Add exllama GPTQ CUDA kernel support () 2023-07-21 10:59:00 +02:00
setup.py feat: add cuda memory fraction () 2023-07-24 11:43:58 +02:00