hosting-7B-llm-on-google-cloud
PublicSpeed benchmarking a 7B LLM on different gcloud VMs (using llama.cpp)
agentbenchmarkbenchmarkingcompute-enginegoogle-cloudgoogle-cloud-platformgpuinternlminternlm-7binternlm-chat-7b
Creat:2024-07-22T22:10:34
Update:2024-10-12T20:05:00
0
Stars
0
Stars Increase