sxy

Results 1 comments of sxy

[Bug]: `size_k must divisible by BLOCK_SIZE_K` error when using tensor parallelism with AWQ-quantized MoE models

The enviroment: **8 A800-40G** docker ： vllm/vllm-openai:latest pip3 list |grep vllm **vllm 0.9.1** root@lx-a800-403-j11-16u:/vllm-workspace# nvcc --version nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2025 NVIDIA Corporation Built on Fri_Feb_21_20:23:50_PST_2025...