Follow
SpecInfer: Accelerating Generative Large Language Model Serving with Speculative Inference and Token Tree Verification. (arXiv:2305.09781v2 [cs.CL] UPDATED)
SpecInfer: Accelerating Generative Large Language Model Serving with Speculative Inference and Token Tree Verification. (arXiv:2305.09781v2 [cs.CL] UPDATED)