Fast_dLLM_v2_1.5B. Artifact for "Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs" [arXiv '25]

github.com/ruipeterpan/Fast_dLLM_v2_1.5B
by @ruipeterpan

Problem

Audience

Keep exploring

Updates

No founder updates yet. Check back soon.