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