search

neuralmagic / nm-vllm

A high-throughput and memory-efficient inference and serving engine for LLMs
https://nm-vllm.readthedocs.io
Other
251 stars 10 forks source link

[ BugFix ] Prompt Logprobs Detokenization (#6223) #378

Closed robertgshaw2-neuralmagic closed 3 months ago

robertgshaw2-neuralmagic commented 4 months ago

SUMMARY: