8fac4b1cc8
EAGLE3 is an encoder-decoder based speculative decoding method: - Extracts features from target model at specific layers - Uses feature fusion layer to compress target features - Generates draft tokens with single-layer decoder - Maps draft vocabulary to target vocabulary via d2t tensor Key changes: - Add LLM_ARCH_EAGLE3 architecture - Add EAGLE3 encoder/decoder graph (src/models/eagle3.cpp) - Add feature extraction from target model layers - Add g_embeddings handling for decoder input - Add GGML_TENSOR_FLAG_SYNC for GPU synchronization - Add --eagle3 flag for speculative-simple example - Add EAGLE3 model conversion in convert_hf_to_gguf.py |
||
|---|---|---|
| .. | ||
| scripts | ||
| __init__.py | ||
| constants.py | ||
| gguf.py | ||
| gguf_reader.py | ||
| gguf_writer.py | ||
| lazy.py | ||
| metadata.py | ||
| py.typed | ||
| quants.py | ||
| tensor_mapping.py | ||
| utility.py | ||
| vocab.py | ||