vLLM compatibility and concurrency
#1
by chatboo - opened
Can this be run with vLLM / Orpheus speech and concurrent requests? Cheers.
Unsure unfortunately. Uou might need to ask the vLLM team or test it π
Thanks I did a GPTQ export any way
Can this be run with vLLM / Orpheus speech and concurrent requests? Cheers.
Unsure unfortunately. Uou might need to ask the vLLM team or test it π
Thanks I did a GPTQ export any way