[AUTOMATED] Model Memory Requirements
#6 opened 5 months ago
by
model-sizer-bot
为啥没有 Qwen2-57B-A14B-Instruct-GPTQ-Int8?
#5 opened 5 months ago
by
Vaccummer
使用vLLM的时候,会报错:CUDA out of memory
1
#3 opened 5 months ago
by
zhaoyang0618