AlpinDale 41beab5dc1 add exllamav2 tensor paralell, fused MoE for GPTQ/AWQ 10 달 전
..
quant c41462cfcd feat: exllamav2 quantization (#305) 11 달 전
compat.cuh c41462cfcd feat: exllamav2 quantization (#305) 11 달 전
matrix_view.cuh c41462cfcd feat: exllamav2 quantization (#305) 11 달 전
q_gemm_exl2.cu 41beab5dc1 add exllamav2 tensor paralell, fused MoE for GPTQ/AWQ 10 달 전
q_gemm_kernel.cuh 41beab5dc1 add exllamav2 tensor paralell, fused MoE for GPTQ/AWQ 10 달 전
q_matrix.cu 41beab5dc1 add exllamav2 tensor paralell, fused MoE for GPTQ/AWQ 10 달 전
q_matrix.cuh c41462cfcd feat: exllamav2 quantization (#305) 11 달 전