recipes
← Back to recipes

glm-4.7-flash-awq

vllmtorch@eugr

vLLM serving cyankiwi/GLM-4.7-Flash-AWQ-4bit with speed optimization patch

Quick Info

Modelcyankiwi/GLM-4.7-Flash-AWQ-4bit
Runtimevllm (torch)
Tensor Parallel1
Nodes1+
Dtypeawq4
Containervllm-node-tf5

Command Builder

sparkrun run @eugr/glm-4.7-flash-awq