#
eagle4
Here are 2 public repositories matching this topic...
Train and adapt speculative decoding drafts for LLM inference: DSpark, DFlash, DFlash2, EAGLE3, and official EAGLE4 checkpoints.
pytorch llm-serving vllm llm-inference speculative-decoding sglang eagle3 dflash dspark dflash2 eagle4
-
Updated
Nov 5, 2026 - Python
Add this topic to your repo
To associate your repository with the eagle4 topic, visit your repo's landing page and select "manage topics."