yahavb
/

inf2-bs32-tp16-mml16k-llama-31-8b-vllm

Model card Files Files and versions Community

inf2-bs32-tp16-mml16k-llama-31-8b-vllm / model.pt

Commit History

Add NxD compiled model yahavb/inf2-bs32-tp16-mml16k-llama-31-8b-vllm for vLLM; after converting checkpoints

afe0afe
verified

yahavb commited on 1 day ago