david/aphrodite-engine: PygmalionAI's large-scale inference engine pygmalion.chat It is designed to serve as the inference endpoint for the PygmalionAI website, and to allow serving the Pygmalion models to a large number of users with blazing fast speeds (thanks to vLLM's Paged Attention). @ a660c69b482b691ea2d9ccebc4f015d44382b8c6

AlpinDale 887e03669a feat: add exllamav2 for GPTQ (#99)		1 vuosi sitten
..
compat.cuh	887e03669a feat: add exllamav2 for GPTQ (#99)	1 vuosi sitten
exllama_ext.cpp	887e03669a feat: add exllamav2 for GPTQ (#99)	1 vuosi sitten
matrix_view.cuh	887e03669a feat: add exllamav2 for GPTQ (#99)	1 vuosi sitten
old_matmul_kernel.cu	887e03669a feat: add exllamav2 for GPTQ (#99)	1 vuosi sitten
q_gemm.cu	887e03669a feat: add exllamav2 for GPTQ (#99)	1 vuosi sitten
q_gemm.cuh	887e03669a feat: add exllamav2 for GPTQ (#99)	1 vuosi sitten
q_gemm_kernel_gptq.cuh	887e03669a feat: add exllamav2 for GPTQ (#99)	1 vuosi sitten
q_matrix.cu	887e03669a feat: add exllamav2 for GPTQ (#99)	1 vuosi sitten
q_matrix.cuh	887e03669a feat: add exllamav2 for GPTQ (#99)	1 vuosi sitten
qdq_4.cuh	887e03669a feat: add exllamav2 for GPTQ (#99)	1 vuosi sitten
qdq_util.cuh	887e03669a feat: add exllamav2 for GPTQ (#99)	1 vuosi sitten