vllm/csrc/quantization/awq
2024-01-26 23:53:17 -08:00
..
dequantize.cuh workaround of AWQ for Turing GPUs (#1252) 2023-10-10 19:48:16 -07:00
gemm_kernels.cu AWQ: Up to 2.66x higher throughput (#2566) 2024-01-26 23:53:17 -08:00